Uploaded May 2025 | Updated November 2026, 17 hours ago
[2025 - Day 1 - Lunch & Learn] George Fraser shares insights from building queryable analytics powerhouses using open-source tools, exploring how to combine DuckDB, Fivetran, and Polaris Catalog to get cloud warehouse ease without the cost and lock-in. For teams frustrated with expensive data warehouses or restrictive platforms, this session offers valuable perspectives on leveraging Iceberg open table format and new dbt adapters for advanced analytics and AI applications.
ABOUT THE SPEAKER:
George Fraser, Co-Founder & CEO, Fivetran -
ποΈ GET YOUR TICKET TO AI COUNCIL 2026 ποΈ
Meet the world's top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
β aicouncil.com/sf-2026
β‘ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: linkedin.com/company/aicouncilconf
Website: aicouncil.com
[2025 - Day 1 - Lunch & Learn] George Fraser shares insights from building queryable analytics powerhouses using open-source tools, exploring how to combine DuckDB, Fivetran, and Polaris Catalog to get cloud warehouse ease without the cost and lock-in. For teams frustrated with expensive data warehouses or restrictive platforms, this session offers valuable perspectives on leveraging Iceberg open table format and new dbt adapters for advanced analytics and AI applications.
ABOUT THE SPEAKER:
George Fraser, Co-Founder & CEO, Fivetran -
ποΈ GET YOUR TICKET TO AI COUNCIL 2026 ποΈ
Meet the world's top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
β aicouncil.com/sf-2026
β‘ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: linkedin.com/company/aicouncilconf
Website: aicouncil.com
![Why GPUs Keep Getting Faster While CPUs Stalled - And What It Means for Your Code
[2025 - Day 1 - AI Engineering] Charles Frye shares insights from understanding GPUs for data science workloads, exploring the most important facts and intuitions about GPU architecture that impact system performance. For data scientists working with neural networks on GPU accelerators, this talk offers valuable perspectives on features and phenomena that affect latency and throughput, from silicon layer fundamentals to high-level frameworks like PyTorch and vLLM.
ABOUT THE SPEAKER:
Charles Frye, Developer Advocate, Modal Labs
ποΈ GET YOUR TICKET TO AI COUNCIL 2026 ποΈ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
β https://aicouncil.com/sf-2026
β‘ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Why GPUs Keep Getting Faster While CPUs Stalled - And What It Means for Your Code](https://i.ytimg.com/vi/ch2ODgbJjlA/mqdefault.jpg)
![Write Less More: How Dagster Rebuilt Our Docs From the Ground Up
[2025 - Day 3 - Lightning Talks] Pedram Navid shares insights from rebuilding Dagsters documentation from the ground up using Docusaurus, exploring how to tackle documentation challenges that incremental improvements couldnt solve. For teams struggling with maintaining technical documentation, this talk offers valuable perspectives on when and how to undertake complete rewrites, presented in the style of a Fresh Prince narrative about flipping docs upside down.
ABOUT THE SPEAKER:
Pedram Navid, Head of Data Engineering & Developer Relations, Dagster Labs -
ποΈ GET YOUR TICKET TO AI COUNCIL 2026 ποΈ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
β https://aicouncil.com/sf-2026
β‘ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Write Less More: How Dagster Rebuilt Our Docs From the Ground Up](https://i.ytimg.com/vi/dVB5hLPyHCM/mqdefault.jpg)
![We Solved Agent Building | Vercel
[2026 - DAY 3 - LIGHTNING TALK] The evolution of building our successful internal text-to-SQL agent that currently fields over 1200 requests a day from Vercel. From a simple prompt, to sophisticated agent, and all the steps we built and learned along the way.
SPEAKER:
Andrew Qu - Chief of Software, Vercel
π Sign up for our No BS Newsletter to get the latest technical data & AI content: https://aicouncil.com/newsletter
ABOUT AI COUNCIL:
AI Council brings together the brightest minds in data to share industry knowledge, technical architectures and best practices in building cutting edge data & AI systems and tools.
FIND US:
Website: https://aicouncil.com/
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
X: https://x.com/aicouncilconf We Solved Agent Building | Vercel](https://i.ytimg.com/vi/e8uqeCtoSFw/mqdefault.jpg)
![Engineering Earths Largest Biological Data Pipeline
[2025 - Day 3 - Lightning Talks] Saif Ur-Rehman shares insights from building Basecamp Researchs proprietary digital twin of life on Earth, exploring how their global biological data supply chain enables next-generation foundation models. This talk offers valuable perspectives on tackling the 99.9% knowledge gap in life sciences through heterogeneous multilayer data representations, crucial for teams working with complex experimental workflows and state-of-the-art AI models in biological research.
ABOUT THE SPEAKER:
Saif Ur-Rehman, Data Engineering Lead, Basecamp Research -
ποΈ GET YOUR TICKET TO AI COUNCIL 2026 ποΈ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
β https://aicouncil.com/sf-2026
β‘ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Engineering Earths Largest Biological Data Pipeline](https://i.ytimg.com/vi/ecIT0YLHH7Q/mqdefault.jpg)
![Trillions-to-Reality: How SambaNovaβs Memory-Centric Design Powers Agentic AI & GenAI Workflows
[2025 - Day 3 - Keynote] Sumti Jairath shares insights from building SambaNovas revolutionary memory-centric architecture, exploring how their innovative design powers trillion-parameter models and multi-agent systems with record-breaking performance. This talk offers valuable perspectives on overcoming the memory wall challenge and optimizing data access for enterprise AI applications, crucial for teams scaling generative AI or building autonomous systems.
ABOUT THE SPEAKER:
Sumti Jairath, Chief Architect, SambaNova Systems -
ποΈ GET YOUR TICKET TO AI COUNCIL 2026 ποΈ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
β https://aicouncil.com/sf-2026
β‘ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Trillions-to-Reality: How SambaNovaβs Memory-Centric Design Powers Agentic AI & GenAI Workflows](https://i.ytimg.com/vi/eduTe244Na8/mqdefault.jpg)

![Unlocking A/B Testing for B2B
[2025 - Day 1 - Data Science & Algos] Timothy Chan shares insights from handling B2B A/B testing at scale, exploring statistical and technical best practices for companies like Notion, Figma, and Atlassian. Whether youre moving beyond traditional B2C experimentation or optimizing enterprise product testing, this talk offers valuable perspectives on the unique challenges and solutions for B2B experimentation that represents one-third of all modern A/B testing scenarios.
ABOUT THE SPEAKER:
Timothy Chan, Head of Data, Statsig -
ποΈ GET YOUR TICKET TO AI COUNCIL 2026 ποΈ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
β https://aicouncil.com/sf-2026
β‘ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Unlocking A/B Testing for B2B](https://i.ytimg.com/vi/f4seZseaeSM/mqdefault.jpg)
![Building Enterprise Agentic RAG Applications w/ Reduced Hallucinations
[2025 - Day 1 - Workshops] Ofer Mendelevitch shares insights from building context-aware AI assistants using Vectaras Agentic RAG framework, exploring how to develop intelligent systems that reason, plan, and act dynamically with reduced hallucinations. For AI developers and researchers, this workshop offers valuable perspectives on step-by-step agentic application development and enterprise workflow automation, addressing common challenges in autonomous system development.
ABOUT THE SPEAKER:
Ofer Mendelevitch, Developer Relations, Vectara -
ποΈ GET YOUR TICKET TO AI COUNCIL 2026 ποΈ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
β https://aicouncil.com/sf-2026
β‘ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Building Enterprise Agentic RAG Applications w/ Reduced Hallucinations](https://i.ytimg.com/vi/fdVeNXdI8Ro/mqdefault.jpg)
![Building the Database for Trillion-Scale AI Search | turbopuffer
[2026 - DAY 1 - DATA ENG & DATABASES] This talk goes beyond architecture diagrams to share what actually happens when you operate an agentic search engine on trillions of documents. Well dig into how an object storage-native design allows a small team of engineers to manage an AI search engine that scales to:
β’ Peak load of 1M+ writes per second and 30k+ searches per second
β’ 1+ trillion documents
β’ 5+ PB of logical data
β’ 400+ tenants
β’ p90 query latency less than 100 ms
Topics include:
β’ How using a modern storage architecture decreases COGS by 10x or more
β’ Optimizing traditional vector and FTS indexes for the high latency of object storage
β’ Building search algorithms that are fine-tuned for LLM-initiated searches
β’ A simple rate-limiting technique that provides strong performance isolation in multi-tenant environments
β’ Observability, reliability, and performance lessons learned from production incidents.
Viewers will leave with a concrete understanding of how separating storage from compute-and treating object storage as the primary database changes not only the cost structure, but the entire operational model of large-scale AI search.
SPEAKER:
Nikhil Benesch - CTO, turbopuffer
π Sign up for our No BS Newsletter to get the latest technical data & AI content: https://aicouncil.com/newsletter
ABOUT AI COUNCIL:
AI Council brings together the brightest minds in data to share industry knowledge, technical architectures and best practices in building cutting edge data & AI systems and tools.
FIND US:
Website: https://aicouncil.com/
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
X: https://x.com/aicouncilconf Building the Database for Trillion-Scale AI Search | turbopuffer](https://i.ytimg.com/vi/gGgZiThcGyw/mqdefault.jpg)

![Designing & Engineering a Viral Multi-Model AI Workflow
[2025 - Day 3 - GenAI Applications] David Wilson shares insights from scaling LinkedIns viral year-in-review generator that reached 300,000 users and processed over a trillion tokens in two weeks, exploring the technical challenges of multi-model AI architecture under pressure. Whether youre building resilient AI workflows or optimizing inference costs, this talk offers valuable perspectives on 25-step workflows across multiple providers, reducing costs by 85%, and production-ready patterns for parallel model orchestration.
ABOUT THE SPEAKER:
David Wilson, Co-Founder & CEO, Hunch Tools -
ποΈ GET YOUR TICKET TO AI COUNCIL 2026 ποΈ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
β https://aicouncil.com/sf-2026
β‘ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Designing & Engineering a Viral Multi-Model AI Workflow](https://i.ytimg.com/vi/gTQG0SfJb9Y/mqdefault.jpg)