# Event Details - **Event Name**: ODSC AI West 2026 Conference | Open Data Science Conference - **Event Start and End Date**: Tue, 27 Oct, 2026 at 09:00 am – Thu, 29 Oct, 2026 at 05:30 pm (-07:00) - **Event Description**: We've just launched our sales! Be among FIRST 100 and prepare to enhance your AI abilities with cutting-edge tools, themes, and insights.About this EventAre you ready to experience the leading technical AI conference at the heart of the AI boom? Accelerate your professional development with hands-on training, talks, workshops, networking events, 10+ tracks, and more.__________________________________ODSC AI West will feature 250+ speakers, instructors, and practitioners, 2,500 of your fellow data and AI practitioners, and hands-on instruction for world-class experts in: https://cdn-az.allevents.in/events1/banners/44bd1cb0-06ce-11f1-ac52-27548aba8e9c-rimg-w1200-h146-dc0d0c0d-gmir.jpg https://cdn-az.allevents.in/events3/banners/44dc3d70-06ce-11f1-a0df-a19131d8c21d-rimg-w1200-h462-dcfefefe-gmir.jpg Join us October 27-29 in San Francisco to celebrate our 11th anniversary with AI’s pioneers. New speaker profiles will be added weekly closer to the event. You’re welcome to check out some speaker blogs .With five passes to choose from, you can personalize your experience and get the most out of ODSC AI West:Silver Pass - 2 days (Wednesday and Thursday) - access to ODSC Keynotes, Talks, and Tutorials, AI Expo & Demo Hall, The AI X Leadership Summit, Networking Reception, Meet the Experts, Dinner with Data Scientists, and other events.Gold Pass - 3 days (Tuesday - Thursday) - everything included in Silver Pass, plus one Extra day, full of Talks, Tutorials, and Hands-on Workshop Sessions, AI Expo & Demo Hall on Tuesday, and other events.Platinum Pass - 3 days (Tuesday - Thursday) - everything included in Gold Pass, with the additions of Deep Dive Training Sessions, held by industry leaders, and other events.AI Mini-Bootcamp Pass - 4 days (Monday (virtual only), Tuesday - Thursday) - everything included in the Platinum Pass plus access to Virtual AI Engineering Accelerator Fundamentals & Pre-Conference Training and a full year of premium subscription to the Ai+ Training Platform.VIP Pass - 4 days (Monday (virtual only), Tuesday - Thursday) - everything included with the Platinum Pass, everything included in the 3-day AI X Leadership Summit Pass, with the additions of daily access to the Speaker/VIP Networking Lunch, Speaker/VIP Lounge, and VIP Fast Lane Registration & Gift Package.IMPORTANT NOTE: All ODSC AI West Passes are strictly non-refundable if the pass holder has attended Agentic AI Summit or Any Pre-conference Accelerator Sessions. https://cdn-az.allevents.in/events5/banners/44fa73d0-06ce-11f1-ac52-27548aba8e9c-rimg-w519-h740-dc010101-gmir.jpg You’ll also be able to build meaningful connections with speakers and peers in a relaxed setting during our networking events like the ODSC AI Networking Reception, Dinner with Data Scientists, Meet the Speaker session, Book Signing sessions, and more. https://cdn-az.allevents.in/events8/banners/4521aae0-06ce-11f1-a773-070e5511f977-rimg-w519-h740-dc020102-gmir.jpg So, are you excited about ODSC AI West in San Francisco? Register now and experience the leading technical AI conference for yourself!What can you expect from an ODSC AI conference? Check out this highlights video from ODSC East 2025. ODSC, where the data community connects. https://cdn-az.allevents.in/events2/banners/4547f790-06ce-11f1-ac52-27548aba8e9c-rimg-w519-h740-dcfefefe-gmir.jpg https://youtu.be/gZkulhJWs_8Ticket prices and availability are subject to increase or decrease, at the discretion of ODSC AI, before and/or after you have made your purchase, and do not entitle the purchaser to a partial refund or credit.Given the nature of live events, changes to specific sessions and/or presenters may be unavoidable and do not entitle the purchaser to a partial (or full) refund or credit. ODSC AI reserves the right to expel and/or void the Ticket of any attendee or participant who violates the .Tuesday, Oct 28A Practical Guide to LLM EvaluationHost: Michelle Yi, Co-Founder at GenerationshipInfo: This session cuts through the noise to provide a hands-on, practical guide for product, business, and technical practitioners tasked with validating LLM-powered systems. We will explore a comprehensive evaluation toolkit that balances cost, speed, and quality. We'll cover the pros and cons of automated metrics (e.g., ROUGE, BLEU), the strategic use of LLM-as-judge frameworks for nuanced qualitative assessment, and best practices for designing efficient and scalable human-in-the-loop evaluation pipelines.5 Rules of Enterprise AI for 2026Host: Cameron Royce, Turner Founder and CEO at TRUIFY.AIInfo: In this 30 minute session, AI veteran Cameron Turner will guide the audience through 5 rules all AI practitioners and decision makers should adhere to when building scaled industrial AI systems. Spanning technical and organizational topics, he will share wins and pitfalls Fortune500/Global1k companies have made in early generative AI adoption and offer practical steps to reduce risk and ensure value creation. With an eye toward sustainability and ethics, Turner will describe how to include governance and human oversight into AI release processes to improve AI performance and ROI for any enterprise. Attendees will leave with a better understanding of the current trends in enterprise AI in 2025, and a practical toolset for building/deploying AI in their environments in 2026.From Automated to Agentic to Scaled AgenticHost: Shikhar Kwatra, AI Architect, OpenAIInfo: Session will include design blueprints/demo, and lessons learned from real production rollouts—enough to start building your own ecosystem, but with plenty still under wraps for the hallway track. Join us to glimpse the agentic future and leave with the roadmap to reach it.Practical Agentic Patterns in ProductionHost: Laurie Voss VP, Developer Relations at LlamaIndexInfo: 2025 is the year of agent: they go beyond basic LLM question-and-answer patterns into an entirely new programming paradigm in which software is given an objective and a set of tools and figures out on its own how to achieve that goal. Agents can not only produce dramatically better, more accurate results in response to queries, but they can be integrated directly into software to accept structured input and take action "under the hood", without needing a chat interface at all. This talk describes practical patterns for building real-world agents including chaining, parallelization and self-reflection, and how to build them in LlamaIndex, with pointers to going deeper to your own "deep research" style agent.Doxing Dark Money: Entity Resolution to Empower Downstream AI ApplicationsHost: Paco Nathan, Principal DevRel Engineer at SenzingInfo: This talk explores known cases, the fraud tradecraft employed, open data sources, and how technology gets leveraged. There are multiple areas were multimodal agentic workflows (e.g., based on BAML) play important roles, both for handling unstructured data sources and for actions taken based on inference. Moreover, we'll look at where data professionals are very much needed, where you can get involved.Best Practises of Applying Llama to Real World: Llama ToolsHost: Sanyam Bhutani, Partner Engineer at MetaInfo: This session is to teach you the best practices of applying llama to your domain. We will learn the best approach to using llama out of box on your domain to get the best performance. The session is split into two parts each are 1 hour long and 25% theory, 75% coding time We will cover automatic prompt optimization using our (entirely) open source repository that helps you minimize engineering time and allows you to focus on prototyping instead of prompt engineering. After maximizing out of box performance, we will focus on the best practices of fine-tuning from cutting edge research and learn how to use synthetic data for your domain.Build Production-Ready Agents With Simple-to-Customize UIsHost: Sandi Besen, AI Research Engineer & Ecosystem Lead | IBMInfo: Join this hands-on workshop to build production-ready agents using BeeAI's framework, then deploy them with out-of-the-box web GUIs through the BeeAI Platform. By session end you'll have built functional agents with built-in observability, memory management, and access to tools, all interactive through an easy-to-configure GUI. Perfect for developers who want powerful AI agents applications without building from scratch.How to Adapt and Thrive in the Age of AI AgentsHost: Julian Bright, Member of Technical Staff at xAI Info: Within five years, AI agents will handle entire feature implementations and production issues autonomously, fundamentally changing what it means to be a software engineer. The traditional individual contributor role will disappear as engineers upskill to delegate, create scalable architectures, and ensure systems operate autonomously. Success will require staying curious and adaptable - continuously learning new tools as models improve. This talk covers two critical areas: reskilling strategies for technical leaders and engineering managers, plus the technical infrastructure needed for human-AI collaboration, including making codebases "agent-ready". Drawing from experience at xAI and building fairgo.ai, you'll gain insights on how to lead in the age of AI agents.From Vision to Orchestration: The Next Generation of AI SystemsHost: Michelle Bonat | Chief AI Officer at AI SquaredInfo: AI has hit a real turning point. Success isn’t just about how accurate a model is anymore. It’s about how well all the pieces work together. The future belongs to systems that are orchestrated, observable, and governed in a way that actually drives results for the business. In this session, I’ll share how that next wave of AI is taking shape. What it looks like when intelligent systems move from isolated experiments to something reliable, measurable, and scalable. I’ve seen this shift firsthand: leading large AI programs at global firms like JPMorgan Chase, serving in C-suite roles at venture-backed startups, and advising early-stage ventures that are building what comes next. What I’ve learned is that the winners aren’t the ones chasing the newest model. They’re the ones building systems that are explainable, auditable, and tied directly to company goals.Running LLMs Locally with Docker Model RunnerHost: Rami Krispin | Senior ManagerInfo: The Docker Model Runner (DMR) is a new feature in Docker Desktop that enables developers to run Large Language Models (LLMs) natively and seamlessly using familiar Docker tools. Its goal is to simplify local AI experimentation by making it easy to set up, test, and integrate models without complex infrastructure. In this workshop, we will explore how DMR can be integrated into your AI development workflow, whether you are already working in containers or not. Participants will learn how to set up DMR locally, import and run LLMs via the Docker CLI and Docker Desktop UI, and extend workflows programmatically using Python with the OpenAI API SDK. By the end, attendees will have the practical skills to run and interact with LLMs locally in a streamlined and reproducible way.How to Adapt and Thrive in the Age of AI AgentsHost: Julian Bright | Member of Technical Staff at xAIInfo: Within five years, AI agents will handle entire feature implementations and production issues autonomously, fundamentally changing what it means to be a software engineer. The traditional individual contributor role will disappear as engineers upskill to delegate, create scalable architectures, and ensure systems operate autonomously. Success will require staying curious and adaptable - continuously learning new tools as models improve. This talk covers two critical areas: reskilling strategies for technical leaders and engineering managers, plus the technical infrastructure needed for human-AI collaboration, including making codebases "agent-ready". Drawing from experience at xAI and building fairgo.ai, you'll gain insights on how to lead in the age of AI agents. Overview The role of software engineer is evolving faster than most realize.Book Author: TECH CONFIDENTIAL: The Insider's Playbook for Daring EntrepreneurHost: Denise Gosnell |Co-Founder, CEO|Data Driven InstitutionsInfo: Join Dr. Denise Gosnell and Kathryn Erickson, authors of Tech Confidential. Drawing on decades of experience in graph data, AI systems, and technology strategy, they offer practical insights on building scalable, trustworthy systems and thriving in high-growth environments, a must-read guide for today’s innovators and entrepreneurs. *Meet the author and get your book signed (limited quantities available)Are Your APIs Ready for AI Agents? A 90-Day Action PlanHost: Sterling Chin | Senior Developer Advocate at PostmanVibe Coding & The Future of Software DevelopmentHost: Ivan Lourenço Gomes | Front-End EngineerInfo: Vibe Coding is changing the way we build software. By combining traditional development with powerful AI tools like ChatGPT, Claude, Gemini, GitHub Copilot, and Lovable, we’re making it easier and faster for anyone to go from idea to execution. This session aims to show how professionals can use these tools to enhance their workflow without losing control of quality, architecture, and security. It is aimed at developers and tech leads who want to rethink how software gets built. We’ll cover real-world use cases where AI helps you move faster, from automating boilerplate and generating clean components, to speeding up refactoring and improving consistency across teams. More importantly, we’ll discuss how to keep the codebase maintainable and scalable when integrating these tools into professional environments. By the end of the session, you’ll have a clearer view of how to work with tools like Copilot and ChatGPT not as shortcuts, but as collaborative partners.Modern Data Architecture in the Cloud EraHost: Sjoukje Zaal | CTO Data & AI Europe at CapgeminiInfo: In today's data-driven world, organizations are rapidly evolving their data architectures to meet the demands of scalability, flexibility, and real-time analytics. This session explores the cutting-edge trends in modern data architecture, focusing on cloud-native solutions, data mesh, data fabric, and data lakehouse concepts. We'll delve into how these architectures are reshaping the data landscape and discuss future trends that will define the next generation of data management.Trust Engineering: The Missing Discipline in Enterprise AIHost: Cal Al-Dhubaib | Head of AI and Data Science at FurtherInfo: Trust is the fundamental currency to AI success. Enterprises already invest in AI and data governance, transparency, customer experience, explainability, and security, but rarely as a unified practice. Trust Engineering brings these fragments together as a discipline to deliver AI solutions that people can rely on. It spans the full lifecycle: from setting user expectations before deployment to designing escalation policies and oversight procedures. This session will show you how to make Trust Engineering part of your AI playbook. Participants will learn to: Define what Trust Engineering is and why it matters in enterprise AI. Identify the core components that belong under Trust Engineering. Spot gaps and overlaps in current governance and reliability efforts. Apply Trust Engineering principles to shape AI strategy and oversight.Best Practices of Applying Llama to Real World: Llama ToolsHost: Sanyam Bhutani | Partner Engineer at MetaInfo: This session is to teach you the best practices of applying llama to your domain. We will learn the best approach to using llama out of box on your domain to get the best performance. The session is split into two parts each are 1 hour long and 25% theory, 75% coding time We will cover automatic prompt optimization using our (entirely) open source repository that helps you minimize engineering time and allows you to focus on prototyping instead of prompt engineering. After maximizing out of box performance, we will focus on the best practices of fine-tuning from cutting edge research and learn how to use synthetic data for your domain.Building Performant & Scaled Agentic Vector SearchHost: Thierry Damiba | Developer Advocate at QdrantInfo: AI agents have grown from simple Q&A chatbots into systems that can independently plan, retrieve, act, and verify tasks. Yet most pilots break moving from prototype to production for three reasons: Memory Loss (agents don’t retain working context across steps or sessions), Fragmented Knowledge (documents, APIs, images, and conversations live in silos), and Fragile at Scale (latency compounds across thousands of calls, precision drops, UX degrades). This session shows how to design reliable agentic search with a real-time memory layer, multimodal support (dense + sparse + hybrid across text, images, and metadata), advanced filtering (semantic + metadata + keyword constraints), and millisecond vector retrieval. We’ll ground concepts with concrete workflows (e.g., planning a Berlin weekend with price, availability, and preference filters) and production patterns that generalize across travel, legal/compliance, support, retail/e-commerce, and field operations. Learning outcomes: 1) PreservCode, Environment, Data: The Holy Trinity of Reproducible ML models with MLfloHost: Amit Kesarwani | Director of Solution ArchitectureInfo: Tired of your MLflow experiments breaking due to hidden data changes? Most ML pipelines overlook dataset versioning, leading to reproducibility nightmares. This talk reveals the hidden pitfalls of unversioned data in MLflow, impacting scaling, collaboration, and validation. We’ll explore why tracking the datasets used in your experiments is critical for ensuring reliable, reproducible results. Without dataset versioning, small changes in data can lead to unpredictable outcomes, making it difficult to scale experiments or collaborate with your team. Join us for a hands-on demo where we’ll show you how to build a robust dataset versioning workflow within your existing MLflow environment. By the end, you’ll understand how to bring clarity to your data, ensure full reproducibility, and avoid the chaos of data discrepancies that can slow down your progress.Accelerate Data Science at Your Desk with Dell and NVIDIAHost: Sama Bali | Senior Product Marketing ManagerInfo: Discover how Dell Pro Max PCs, powered by the latest NVIDIA RTX PRO GPUs and CUDA-X libraries, can transform local data science workflows. This session will show you how to harness accelerated compute right at your desk—enabling lightning-fast data ingestion, curation, exploration, and machine learning—all while ensuring data privacy in a secure, local environment. Through real benchmark results and hands-on demonstrations, you’ll see how GPU-powered analytics empower you to iterate, analyze, and deploy advanced models faster and more efficiently than ever.Test Drive | Dell AI Factory with NVIDIAHost: Jon Presti | Technical Instructor at FireflyInfo: In this session, you will explore real-world deployment patterns for AI and the future of agentic AI systems in this interactive seminar. After a short discussion, you will shift gears and take control: Choose from multiple hands-on-labs and put the Dell AI Factory with NVIDIA test for yourself.Fast, Cost-Efficient Inference to Scale Agentic AIHost: Yunmo Koo | Software Engineer at FriendliAIInfo: Agentic AI, systems that plan, reason, and act across multiple steps, is rapidly becoming central to modern applications across industries. Yet the same capabilities that make these systems powerful also amplify inference challenges. Long-running sessions, repeated tool calls, and complex orchestration increase latency, drive up GPU costs, and reduce reliability, often preventing teams from moving beyond prototypes to scalable production deployments. In this demo talk, we will showcase how the Friendli Suite, FriendliAI’s inference platform, simplifies and accelerates agentic AI at scale. Through live demonstrations, attendees will see how advanced inference optimizations are built into production-ready API endpoints, removing the need for deep systems expertise. The session is designed for data scientists, ML engineers, and technical leaders looking to deploy their own or open-source models without infrastructure overhead.A Visual Guide to AI AgentsHost: Maarten Grootendorst | Lead Data ScientistInfo: Driven by the rapid advances in deep learning, language AI systems are developing at an unprecedented pace. We are approaching a new field of AI where autonomous systems, or AI Agents, think and act for themselves with limited human interaction. These AI Agents have evolved beyond simple task execution and are capable of independent reasoning, planning, and decision-making. In this visual and animated presentation, we will go through the fundamentals of AI Agents, including reasoning LLMs, memory, tools, and planning. Attendees will learn the fundamentals of AI agents, how they work, and what makes them different from regular LLMs.CHECK MORE SESSIONS ON OUR WEBSITEHost: More Speakers Joining!Info: https://schedule.odsc.ai/Wednesday, Oct 29ODSC Keynote: Context Engineering for AI AgentsHost: Harrison Chase, CEO and Co-founder at LangChainInfo: Description coming soon!How to Train Your Agent: Building Reliable AgentsHost: Kyle Corbitt, Co-Founder and CEO at OpenPipeInfo: DESCRIPTION COMING SOON!Mastering Visual AI with Vision-Language Models, Advanced Evaluation TechniqueHost: Harpreet Sahota, Hacker-in-Residence at Voxel51Info: This hands-on workshop explores computer vision techniques for automotive damage detection using the CarDD dataset - the largest public dataset specifically designed for vehicle damage analysis. Participants will learn how to leverage FiftyOne, a powerful computer vision experimentation platform, to explore, visualize, and build models for detecting six common types of vehicle damage: dents, scratches, cracks, glass shatter, tire flats, and broken lamps. This workshop is designed for computer vision practitioners, automotive industry professionals, and data scientists interested in applying modern deep learning techniques to vehicle damage detection. Participants will gain practical experience working with a production-grade dataset while learning best practices for model development, evaluation, and deployment.The Anatomy of an AgentHost: Zain Hasan, PhD, Staff AI/ML Engineer at Together AIInfo: DESCRIPTION COMING SOON!Building Dynamic In-Context Learning for Self-Optimizing AgentsHost: Amy Hodler, Executive Director at GraphGeeks.org Info: Language models have been observed to have emergent capabilities that extend past the distribution of their training data. This technical tutorial explores the practical implementation of a novel dynamic in-context learning (dICL) system within a Graph RAG agentic workflow. We will begin by reviewing the foundational concepts of in-context learning, where Large Language Models (LLMs) adapt to tasks by leveraging examples directly within their input prompts. We will then introduce self-optimizing agents, which extend LLMs with capabilities for real-time and continuous self-improvement through context optimization. While traditional ICL is often static, our approach demonstrates how to create a dynamic feedback loop that enables an agent to learn and adapt in real-time from its own performance. This system integrates Comet Opik for robust evaluation and LanceDB as a vector-native database for efficient knowledge management.Orchestrating Workflows for GenAI Applications with Apache AirflowHost: Kenten Danas, Senior Manager of Developer RelationsInfo: Productionizing GenAI applications often relies on multi-stage, complex pipelines that manage data ingestion, creation of vector embeddings, vector storage, querying, and response construction. These pipelines need to run reliably, scale efficiently, and recover from failure without manual intervention. Apache Airflow, a leading open-source orchestration framework, provides the structure and flexibility required to operationalize GenAI workloads with production-grade reliability. In this workshop, you'll learn the basics of using Airflow to build and orchestrate end-to-end GenAI workflows. We’ll explore orchestration through the lens of a Retrieval-Augmented Generation (RAG) use case: a book recommendation system that embeds book descriptions, loads them into a vector database, queries them based on user input, and provides LLM-generated summaries.Context Engineering: A State-of-the-Art OverviewHost: Greg Loughnane, Co-Founder & CEO at AI MakerspaceInfo: DESCRIPTION COMING SOON!AI Driven Automation in Open-Source Metadata Platforms: Embedding MCP ServerHost: Nick Acosta, Developer Advocate at CollateInfo: Model Context Protocol (MCP) is an open protocol for AI agent communication that is revolutionizing how AI agents interact with data, and its possibilities for automation and intelligent management erupt when metadata is included. OpenMetadata is an open-source platform that centralize metadata to empower teams to build and manage high-quality data assets through data discovery, observability, and governance. By combining the two, organizations can transform their data operations, realize new ways of efficiency, and unlock the full potential of their data assets. Join us in this hand-on workshop (or talk) as we: - Introduce both OpenMetadata and MCP Servers and their impact on a data stack - Explain architecture motivations for embedding MCP into an open metadata platform instead of using it as a standalone server - Walkthrough transformational use cases for AI to use metadata to proactively identify and fix data quality issues or enforce access and ownership policiesToward SuperIntelligenceHost: Vedant Misra, AI Researcher at Google DeepMindInfo: DESCRIPTION COMING SOON!Buckle Up: How Waymo Uses Data to Create a Safer Driving ExperienceHost: Manasi Joshi, Director, Systems Intelligence and MLInfo: Powered by 100 million miles on public roads and billions more in simulation, the Waymo Driver is the most advanced application of AI in the physical world today. Waymo collects massive amounts of data from real roads and billions of miles driven in computer simulations. Manasi Joshi, director of Systems Intelligence and Machine Learning, will explain how Waymo's engineers use these huge datasets to advance how cars "see" the world, predict what other drivers will do, and plan their routes. You'll hear about how Waymo uses ML to train and test these self-driving systems and how its open dataset is motivating further public research in autonomy. This work helps make Waymo's autonomous vehicles safer and more reliable every day in an era of rapid expansion and competition of autonomous ride-hailing services.Unleashing Enterprise AI: Bridging Innovation and PracticalityHost: Helen O’Sullivan | AI Solutions Specialist ManagerInfo: AI is revolutionizing industries, but its full potential remains untapped without the right infrastructure and strategy. This session explores how Dell AI Factory, in partnership with NVIDIA, empowers enterprises to overcome challenges like skill gaps, data management, and security concerns. Learn how to move from experimentation to production-ready AI deployments with confidence. Takeaways: - Understand the critical role of purpose-built AI infrastructure in accelerating innovation. - Discover real-world examples of AI success in healthcare, finance, and manufacturing. - Learn how to start small, tackle key challenges, and scale AI solutions effectively.Approaches to AI alignmentHost: Emmett Shear | Co-founderAuthors: 'The Practitioner's Guide to Graph Data' & 'Graph Algorithms'Host: Denise Gosnell | Data Driven IntuitionInfo: Denise Gosnell and Amy Hodler are leading voices in graph technologies, with decades of experience advancing graph analytics and AI. Their books, The Practitioner’s Guide to Graph Data and Graph Algorithms, are foundational texts that demonstrate how graphs unlock hidden patterns and enable cutting-edge AI applications. Meet the author and get your book signed (limited quantities available)Introduction to Model Context ProtocolHost: Valentina Alto | Technical Architect, AI&App, MicrosoftInfo: AI agents are rapidly becoming a key pattern for building intelligent applications—combining reasoning, memory, and tool use to solve complex tasks. Yet, one of the biggest hurdles AI Developers face is equipping these agents with tools which live in a very fragmented ecosystems. This is where the Model Context Protocol (MCP) comes in. In this session, we introduce MCP as an open protocol designed to make AI agents more interoperable, extensible, and production-ready. We will walk through how MCP defines a common way for agents to discover and use external tools, exchange context, and collaborate with other systems. By the end of the session, attendees will understand the core concepts and architecture of MCP and how MCP enhances AI agent capabilities with consistent tool and context integration.Scaling Distributed Multimodal Training with RayHost: Suman Debnath | Technical Lead (ML) at AnyscaleInfo: As multimodal AI workflows surge in complexity and scale, integrating image, text, audio, and other unstructured data engineering teams face growing challenges in orchestration, reliability, and production deployment. This talk dives into Ray Distributed AI Computing framework for data preparation, training and online serving at scale showcasing how Ray Train simplifies scalable, reliable, end-to-end distributed training workflows.Agentic by Design: Moving from Automated Tools to Scalable OrchestrationsHost: Shikhar Kwatra | AI Architect at OpenAIInfo: Automation is no longer about wiring APIs together; it’s about launching self-directed agents that negotiate, learn, and act on our behalf. This keynote charts the leap from single-task scripts to large-scale, self-optimizing agent networks. You’ll see: - Orchestration Patterns that keep a multi-agent swarm safe, steerable, and debuggable. - The Optimization Flywheel that turns traces into evals into better models—on repeat. - A Unified Data Layer that lets agents remember, personalize, and collaborate across sessions. Session will include design blueprints/demo, and lessons learned from real production rollouts—enough to start building your own ecosystem, but with plenty still under wraps for the hallway track. Join us to glimpse the agentic future and leave with the roadmap to reach it.Visualization in Bayesian WorkflowHost: Clinton Brownley, Ph.D | Lead Data Scientist at TalaInfo: Visualization can be a powerful tool to help you build better statistical models. In this tutorial, you will learn how to create and interpret visualizations that are useful in each step of a Bayesian workflow for common linear, generalized linear, and multilevel regression models. A Bayesian workflow includes the three steps of (1) model building, (2) model interpretation, and (3) model checking/improvement, along with comparisons to other models. Visualization is helpful in each of these steps – generating graphical representations of the model and plotting prior distributions aid modeling building, visualizing MCMC diagnostics and plotting posterior distributions aid interpretation, and plotting posterior predictive, counterfactual, and model comparisons aid model checking/improvement.Practical Guide to Agentic OrchestrationsHost: Lorenze Jay Hernandez |Open Source Lead Engineer|Crew AIInfo: In the evolving landscape of intelligent systems, orchestrating multi-agent workflows is both a powerful opportunity and a nuanced design challenge. This talk offers a practical framework for understanding and deploying agentic orchestrations—from fully autonomous multi-agent systems to tightly controlled, high-precision task flows. We’ll explore a spectrum of orchestration strategies suited to different levels of task complexity, required precision, and human-in-the-loop control. Through real-world use cases, we’ll compare orchestration types collaboration styles (crews and flows) and examine when to favor autonomy over intervention—or vice versa. Attendees will leave with a clear mental model of orchestration types and a practical guide for selecting the right approach based on system goals, risks, and constraints. From Data to Decisions: A Hands-On Introduction to Optimal Decision MakingHost: Summer Purschke | Technical Account Manager at GurobiInfo: Many AI tools uncover patterns, analyze systems, and summarize information—but making the best decision requires optimization. In this hands-on workshop, you’ll learn how to use mathematical optimization to go beyond predictions: allocating resources, planning schedules, and solving complex business problems with confidence. We’ll introduce optimization as a well-established AI technique and guide you through building and solving your first model in Python. You’ll leave with a powerful new tool in your AI toolbox to turn data into actionable, high-impact decisions.You Can’t Do AI Without Quality APIsHost: Talia Kohan | Staff Developer Advocation at PostmanInfo: AI agents don’t actually do anything on their own. They don’t fetch data, they don’t book meetings, they don’t trigger workflows. They call APIs. That means if you can build APIs, you can build AI. Here’s the catch: REST APIs power the web, but they weren’t designed with AI in mind. For APIs to be truly useful, and usable by AI systems (especially agents and LLMs), they need to have eight critical characteristics. In this talk, we’ll explore how APIs are shaping the future of intelligent automation. Using real-world examples from across industries, we’ll examine how companies are leveraging APIs to orchestrate multi-step workflows, access real-time data, and drive operational efficiency with AI. Organizations with robust, scalable, and discoverable API ecosystems will not only keep up, they’ll lead. If AI is the recipe, APIs are the ingredients. It's time we start treating them that way.Intro to Multi-Agent Systems with the A2A ProtocolHost: Holt Skinner | Developer Advocate at Google Cloud AIInfo: The Agent2Agent (A2A) Protocol is an open standard, created by Google and donated to the Linux Foundation, designed to enable seamless communication and collaboration between AI agents. In a world where agents are built using diverse frameworks and by different vendors, A2A provides common terminology, data structures, and methods for agents to communicate and collaborate on tasks, making it possible to build scalable, cross-organization multi-agent systems. In this session, we will learn about the A2A protocol and how to implement it in agentic systems using the A2A Python SDK. Attendees will learn about the key components of the A2A Protocol and how to implement it using the A2A SDK and various agentic frameworks (Google ADK, BeeAI, LangGraph,)Scaling Inference for Generative AIHost: Byung-Gon Chun | Founder & CEO at FriendliAIInfo: As generative AI adoption accelerates, the greatest challenge lies in scaling workloads from prototypes to production. Latency, cost, and reliability remain the three most pressing hurdles—low latency is essential for responsive user experiences, cost efficiency determines long-term viability, and reliability is indispensable for mission-critical, enterprise-grade deployments where even small disruptions can have a significant business impact. GPU management complexity only compounds these issues, often stalling progress when organizations attempt to move beyond the prototype stage. This talk explores essential strategies such as quantization, batching, caching, and hardware-aware optimizations that bridge the gap between research results and production-grade performance.Building Efficient AI Agents with FriendliAI: From Optimization to DeploymentHost: Harini Dalta | Customer Success Engineer at FriendliAIInfo: Agentic AI systems, integrating reasoning, memory, and tool use, are revolutionizing user interaction. However, large-scale model inference poses challenges due to high latency, GPU costs, and optimization trade-offs. This hands-on workshop will demonstrate building and deploying production-ready AI agents using FriendliAI's inference platform (Friendli Suite). We'll show how Friendli Endpoints abstract various inference optimizations, enabling rapid deployment of multi-agent workflows. Attendees will deploy a lightweight agent, experience optimization effects, and gain practical skills for scaling agentic AI reliably and cost-effectively.Building Dynamic In-Context Learning for Self-Optimizing AgentsHost: Amy Hodler | Executive Director at GraphGeeks.orgInfo: Language models have been observed to have emergent capabilities that extend past the distribution of their training data. This technical tutorial explores the practical implementation of a novel dynamic in-context learning (dICL) system within a Graph RAG agentic workflow. We will begin by reviewing the foundational concepts of in-context learning, where Large Language Models (LLMs) adapt to tasks by leveraging examples directly within their input prompts. We will then introduce self-optimizing agents, which extend LLMs with capabilities for real-time and continuous self-improvement through context optimization. While traditional ICL is often static, our approach demonstrates how to create a dynamic feedback loop that enables an agent to learn and adapt in real-time from its own performance. This system integrates Comet Opik for robust evaluation and LanceDB as a vector-native database for efficient knowledge management.Superhuman Code, Now What?Host: Jepson Taylor | Founder & CEO at VEOXInfo: We’ve spent a decade tuning models. Now the frontier is inventing the methods themselves. In this session, Jepson introduces Engineered Intelligence (EI): agentic systems that design models, objectives, search strategies, and threshold policies on demand, under your guardrails for cost, latency, and safety. We’ll open the hood on algorithm decomposition (objective / encoder / search / calibrator) and show how component‐level evolution delivers operating‐point wins (e.g., more fraud caught at the same false‐positive rate). Then we take it further with Generative Reinforcement Learning (GRL)—agents that modify parts of the algorithm live as environments change. Great for: ML engineers, MLOps, applied researchers, quant/ops leads. You’ll leave with: A mental model for EI, a checklist to productionize agent‐invented methods, and a feel for what “superhuman code” actually looks like on the screen.Complex Data Ingestion with Open Source AIHost: Mingxuan Zhao | Developer Advocate at IBMInfo: If you have worked with AI in any capacity, you'll know that AI is only as valuable as the data in can leverage. Data is the cornerstone of AI, and developers need better ways to transform complex documents into structured data ready for model training and inference. In this session we will learn how to turn common, real-world documents and scans into structured data for search and RAG. In this 90-minute, code-along workshop, you’ll learn the strengths of Docling, an open-source toolkit for advanced document conversion, allowing you to leverage your data more effectively into AI workflows. We’ll complete three labs; Conversion, Chunking, and RAG, and you’ll leave with runnable notebooks from a public GitHub repo. Takeaways By completing this workshop, you will leave knowing how to use Docling to turn messy files into structured, exportable Markdown/JSON documents, how to chunk them smartly for retrieval, and how to build a multimodal RAG workflow using vector stores.CHECK MORE SESSIONS ON OUR WEBSITEHost: https://odsc.ai/west/scheduleThursday, Oct 30Beyond Benchmarks - The widening Gap Between Testing and RealityHost: Sinan Ozdemir, AI Author & Educator | Pearson | O'ReillyInfo: High benchmark scores make for great headlines, but they often mask the messy truth of real-world AI performance and adoption. Recent stories like Meta’s LLaMA-4 benchmark controversy, OpenAI’s GPT-4o “sycophancy” issue, and the bumpy GPT-5 rollout show how easy it is for models to look stellar in controlled tests yet stumble with actual users. Benchmarks tend to be narrow, static, and sometimes irrelevant or compromised by data leakage or over-optimization. This talk makes the case that AI evaluation must go beyond leaderboard bragging rights to focus on the realities of each organization’s unique environment. We’ll explore how and why the gap between benchmark scores and real-world results is widening, drawing on timely case studies and industry trends. Attendees will learn practical methods to create internal benchmarks, stress-test and experiment with models for their own use cases, and monitor them post-deployment to catch behavioral drift, hallucinations, or biases.Context Engineering with LangGraphHost: Sydney Runkle, Software Engineer at LangChainInfo: Context engineering is the art of dynamically filling an LLM's context window with the right information to help it perform a task to the best of its ability. It's most often the case that when an LLM isn't performing as expected, it's because it doesn't have access to the relevant information needed to succeed. This becomes an especially challenging task for agentic systems, where conversations can span tens or hundreds of turns. Relevant information can rapidly balloon and exceed context window limits, and outdated context can even sabotage the agent's past progress. As a result, sophisticated systems must be in place to intelligently persist, filter, and evolve context throughout agent runs. Consequently, context engineering has emerged as one of the most critical skills that AI engineers can develop.Vibe Coding & The Future of Software DevelopmentHost: Ivan Lourenço Gomes, Front-End Engineer & TechnologyInfo: Vibe Coding is changing the way we build software. By combining traditional development with powerful AI tools like ChatGPT, Claude, Gemini, GitHub Copilot, and Lovable, we’re making it easier and faster for anyone to go from idea to execution. This session aims to show how professionals can use these tools to enhance their workflow without losing control of quality, architecture, and security. It is aimed at developers and tech leads who want to rethink how software gets built. We’ll cover real-world use cases where AI helps you move faster, from automating boilerplate and generating clean components, to speeding up refactoring and improving consistency across teams. More importantly, we’ll discuss how to keep the codebase maintainable and scalable when integrating these tools into professional environments. By the end of the session, you’ll have a clearer view of how to work with tools like Copilot and ChatGPT not as shortcuts, but as collaborative partners.Building Robotics Foundation ModelsHost: Lili Yu, Research Scientist at Physical IntelligenceInfo: DESCRIPTION COMING SOON!AI Software Engineering AgentsHost: Robert Brennan, CEO at All Hands AIInfo: DESCRIPTION COMING SOON!Basic Theory and Practice of Fine-Tuning LLMs with PPO and GRPOHost: Seth Weidman, Principal Product Manager at SentiLink Info: DESCRIPTION COMING SOON!Building Data Contracts with Open Source ToolsHost: Jean-Georges Perrin, Senior Product Manager at ActianInfo: DESCRIPTION COMING SOON!How to Build and Deploy Agentic SystemsHost: Paige Bailey | DevRel Lead, GenAI at GoogleSession by Emma Brunskill Coming Soon!Host: Emma Brunskill | Associate Professor of Computer ScienceBuilding, Deploying and Scaling Agents in ProductionHost: João (Joe) Moura | CEO at CrewAIInfo: In this keynote address, Joao Moura, CEO of CrewAI, will guide the audience through a comprehensive exploration of the rapidly emerging world of AI Agents. He will explain what AI Agents are, why leading enterprises are increasingly establishing mandates to deploy them in real-world environments, and how these intelligent systems are transforming the way organizations operate. Joao will also highlight the key strategies, frameworks, and best practices for building, deploying, and scaling agents successfully into production. Attendees will gain both a high-level perspective on the evolving AI Agent landscape and practical insights into what it takes to harness their full potential within enterprise settings.Beyond LLMs: Exploring Program Synthesis for ARC-AGI and Abstract ReasoningHost: Clem Bonnet | Member of Technical Staff at NdeaInfo: Large Language Models (LLMs) have advanced natural language processing and general AI benchmarks, but they continue to struggle with compositional reasoning tasks such as those found in the Abstraction and Reasoning Corpus (ARC-AGI). In this hands-on workshop, we will explore approaches to abstract reasoning beyond LLMs, focusing on program synthesis for solving ARC-like challenges. Participants will gain practical exposure to building reasoning systems that operate by composition rather than pure pattern matching. Through guided coding exercises, we’ll walk through benchmarking LLMs, implementing a simple ARC-AGI solver that searches over a space of functional programs, and glancing at more advanced methods, highlighting the importance of composition for generalization and AGI. By the end of the session, attendees will have both an understanding of current limitations of LLMs, a working prototype of a program synthesis solver.Book Author: Quick Start Guide to Large Language ModelsHost: Sinan Ozdemir | AI Author and Educator at PearsonInfo: Sinan Ozdemir, mathematician, AI expert, and early contributor to AI and agent development, has been at the forefront of large language model applications. His Quick Start Guide to Large Language Models offers a clear and structured approach to understanding and leveraging LLMs for real-world innovation. Meet the author and get your book signed (limited quantities available)The next revolution in AI won't unfold behind screens—it will happen in the phHost: Avinash Balachandran | VP at Toyota Research InstituteInfo: The next revolution in AI won't unfold behind screens—it will happen in the physical world. As we merge advanced AI with intelligent hardware, entirely new paradigms of interaction between people and machines are emerging. This talk explores how embodied AI—AI with a physical presence—can become a powerful force in amplifying human capabilities and enriching quality of life. Grounded in Toyota’s core philosophy of human-centered innovation, we examine how intelligent vehicles can evolve beyond passive safety systems into true driving companions. These vehicles won’t just assist; they’ll build relationships with drivers, helping them learn, gain confidence and have fun while driving. We'll extend these insights beyond mobility, revealing how the fusion of AI and embodiment opens up novel ways for people to partner with machines—not just to automate tasks, but to grow, learn, and thrive together.CHECK MORE SESSIONS ON OUR WEBSITEHost: https://odsc.ai/west/schedule - **Event URL**: https://allevents.in/burlingame/odsc-ai-west-2026-conference-|-open-data-science-conference/100001982434744687 - **Event Categories**: workshops, business, it, art, artificial-intelligence, conferences, literary-art, contests, fine-arts, exhibitions, performances, entertainment, nonprofit, meetups, virtual - **Interested Audience**: - total_interested_count: 0 ## Ticket Details - **Ticket URL**: https://consumer.pxf.io/c/1339408/3151484/39691?partnerpropertyid=1191892&MediaPartnerPropertyId=1191892&svlink=14105511&level=1&u=https%3A%2F%2Fwww.eventbrite.com%2Fe%2Fodsc-ai-west-2026-conference-open-data-science-conference-tickets-1982434744687 - **Ticket Price Range**: min: 0, max: 4121.83, currency: USD ## Event venue details - **city**: Burlingame - **state**: CA - **country**: United States - **location**: Hyatt Regency San Francisco Airport - **lat**: 37.5938725 - **long**: -122.3651261 - **full address**: Hyatt Regency San Francisco Airport, 1333 Old Bayshore Highway, Burlingame, United States ## Event Organizer details - **affiliate_id**: 10 - **organizer**: ODSC Team | odsc.com (https://allevents.in/org/odsc-team-|-odsccom/22552053) ## Event gallery - **Alt text**: banner - **Image URL**: https://cdn-az.allevents.in/events5/banners/87bf691444eb255d45b4ad067a3a093389cf56e615203637b6f2a148ed5070ca-rimg-w1200-h600-dc000001-gmir.jpg?v=1770761844 - **Alt text**: thumbnail - **Image URL**: https://cdn-az.allevents.in/events5/banners/71d90a2c5bbc0ccd019c54e0f57b5c92d136a2e3430bd1d45a395957001bc239-rimg-w400-h400-dc000000-gmir.jpg?v=1770761844 ## FAQs - **Q**: When is the event happening? - **A:** Tue, 27 Oct, 2026 at 09:00 am (-07:00) - **Q**: Where is the event happening? - **A:** Hyatt Regency San Francisco Airport, 1333 Old Bayshore Highway, Burlingame, United States - **Q**: What is the ticket price? - **A:** starting from 0 up to 4121.83 USD - **Q**: Who is organizing the event? - **A:** ODSC Team | odsc.com - **Q**: What type of event is this? - **A:** workshops, business, it, art, artificial-intelligence, conferences, literary-art, contests, fine-arts, exhibitions, performances, entertainment, nonprofit, meetups, virtual - **Q**: Where can I find ticket details about ODSC AI West 2026 Conference | Open Data Science Conference ? - **A:** You can find ticket details about this event on AllEvents. ## Structured Data (JSON-LD) ```json [ { "@context": "https://schema.org", "@type": "Event", "name": "ODSC AI West 2026 Conference | Open Data Science Conference", "image": "https://cdn-az.allevents.in/events5/banners/87bf691444eb255d45b4ad067a3a093389cf56e615203637b6f2a148ed5070ca-rimg-w1200-h600-dc000001-gmir.jpg?v=1770761844", "startDate": "2026-10-27T09:00:00-07:00", "endDate": "2026-10-29T17:30:00-07:00", "url": "https://allevents.in/burlingame/odsc-ai-west-2026-conference-|-open-data-science-conference/100001982434744687", "eventStatus": "https://schema.org/EventScheduled", "location": { "@type": "Place", "name": "Hyatt Regency San Francisco Airport", "address": { "@type": "PostalAddress", "streetAddress": "1333 Old Bayshore Highway", "postalCode": "94010", "addressLocality": "Burlingame", "addressRegion": "CA", "addressCountry": "US" }, "geo": { "@type": "GeoCoordinates", "latitude": "37.5938725", "longitude": "-122.3651261" } }, "eventAttendanceMode": "https://schema.org/OfflineEventAttendanceMode", "description": "We've just launched our sales! Be among FIRST 100 and prepare to enhance your AI abilities with cutting-edge tools, themes, and insights.", "offers": [ { "@type": "AggregateOffer", "availability": "https://schema.org/InStock", "priceCurrency": "USD", "availabilityStarts": "2026-02-10", "availabilityEnds": "2026-10-29T17:30:00-07:00", "validFrom": "2026-02-10", "lowPrice": "0.00", "highPrice": "4121.83", "price": "0.00", "url": "https://allevents.in/burlingame/odsc-ai-west-2026-conference-|-open-data-science-conference/100001982434744687" }, { "@type": "Offer", "availability": "https://schema.org/InStock", "priceCurrency": "USD", "availabilityStarts": "2026-02-10", "availabilityEnds": "", "validFrom": "2026-02-10", "url": "https://allevents.in/burlingame/odsc-ai-west-2026-conference-|-open-data-science-conference/100001982434744687", "price": "1649.83", "name": "Silver Pass - 2 Days (Wed & Thu) Talks & Tutorials" }, { "@type": "Offer", "availability": "https://schema.org/InStock", "priceCurrency": "USD", "availabilityStarts": "2026-02-10", "availabilityEnds": "", "validFrom": "2026-02-10", "url": "https://allevents.in/burlingame/odsc-ai-west-2026-conference-|-open-data-science-conference/100001982434744687", "price": "2473.83", "name": "Gold Pass - 3 Day Talks, Tutorials, Workshops" }, { "@type": "Offer", "availability": "https://schema.org/InStock", "priceCurrency": "USD", "availabilityStarts": "2026-02-10", "availabilityEnds": "", "validFrom": "2026-02-10", "url": "https://allevents.in/burlingame/odsc-ai-west-2026-conference-|-open-data-science-conference/100001982434744687", "price": "3297.83", "name": "Platinum Pass - Talks, Workshops & Training" }, { "@type": "Offer", "availability": "https://schema.org/InStock", "priceCurrency": "USD", "availabilityStarts": "2026-02-10", "availabilityEnds": "", "validFrom": "2026-02-10", "url": "https://allevents.in/burlingame/odsc-ai-west-2026-conference-|-open-data-science-conference/100001982434744687", "price": "3709.83", "name": "AI Accelerator Pass - PLUS Pre-Conference Day" }, { "@type": "Offer", "availability": "https://schema.org/InStock", "priceCurrency": "USD", "availabilityStarts": "2026-02-10", "availabilityEnds": "", "validFrom": "2026-02-10", "url": "https://allevents.in/burlingame/odsc-ai-west-2026-conference-|-open-data-science-conference/100001982434744687", "price": "4121.83", "name": "VIP Pass - Everything in one" }, { "@type": "Offer", "availability": "https://schema.org/InStock", "priceCurrency": "USD", "availabilityStarts": "2026-02-10", "availabilityEnds": "", "validFrom": "2026-02-10", "url": "https://allevents.in/burlingame/odsc-ai-west-2026-conference-|-open-data-science-conference/100001982434744687", "price": 0, "name": "Group booking expression of interest" }, { "@type": "Offer", "availability": "https://schema.org/InStock", "priceCurrency": "USD", "availabilityStarts": "2026-02-10", "availabilityEnds": "", "validFrom": "2026-02-10", "url": "https://allevents.in/burlingame/odsc-ai-west-2026-conference-|-open-data-science-conference/100001982434744687", "price": 0, "name": "Support Ukraine" } ], "organizer": [ { "@type": "Organization", "name": "ODSC Team odsc.com", "url": "https://allevents.in/org/odsc-team-|-odsccom/22552053", "description": "The Open Data Science Conference brings together leaders and practitioners in the open source and data science communities to teach the tools, languages and technologies used in applied data science and AI." } ] } ] ```