Uploaded May 2025 | Updated September 2026, 2 weeks ago
[2025 - Day 1 - Workshops] Ofer Mendelevitch shares insights from building context-aware AI assistants using Vectara's 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 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 - Workshops] Ofer Mendelevitch shares insights from building context-aware AI assistants using Vectara's 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 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
![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)

![Internals of SlateDB: An Embedded Key Value Store Built On Object Storage
[2025 - Day 2 - MLOps & Platforms] Vignesh Chadramohan shares insights from building SlateDB, an embeddable storage engine built on object storage, exploring how to leverage properties like conditional writes for stream processing and durable execution. Whether youre working with disaggregated data systems or building on S3-like storage, this talk offers valuable perspectives on implementing features like checkpoints, writeable clones, and remote compaction in Rust-based storage engines.
ABOUT THE SPEAKER:
Vignesh Chadramohan, Engineering Manager, DoorDash -
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/ Internals of SlateDB: An Embedded Key Value Store Built On Object Storage](https://i.ytimg.com/vi/gcTRXZeKbNg/mqdefault.jpg)
![From Concurrency Control to Concurrent Scheduling
[2025 - Day 3 - Databases] Natacha Crooks explores how database concurrency control has evolved from traditional locking mechanisms to modern concurrent scheduling approaches in distributed systems. Drawing from her research at the intersection of databases and distributed systems, she examines the practical tradeoffs between performance and fault-tolerance when coordinating parallel operations at scale, providing actionable insights for engineers building high-throughput systems where classic coordination methods often fall short.
ABOUT THE SPEAKER: Natacha Crooks, Assistant Professor, UC Berkeley; Visiting Researcher, Azure Systems 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/ From Concurrency Control to Concurrent Scheduling](https://i.ytimg.com/vi/hSEl_Te-t1o/mqdefault.jpg)
![The Art of Data: Reimagining Creative Processes with Data Culture
[2025 - Day 3 - Lightning Talks] Michael Cohen shares insights from bridging the gap between artistic creativity and data intelligence, exploring strategies to foster a culture where data fuels rather than stifles creative expression. For leaders working across creative and analytical teams, this talk offers valuable perspectives on overcoming perception barriers, fostering data literacy among creatives, and implementing data storytelling approaches that enhance impactful creativity and collaboration.
ABOUT THE SPEAKER:
Michael Cohen, Global Chief Data & Analytics Officer, Plus Company -
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/ The Art of Data: Reimagining Creative Processes with Data Culture](https://i.ytimg.com/vi/hYpl0mVPkbc/mqdefault.jpg)
![What comes after Deep Learning? | Incept Labs
[2026 - DAY 1 - INFERENCE SYSTEMS] I will go over the history of building blocks that are underlying the foundations of modern learning algorithms. These building blocks are outdated and the recent agentic revolution makes them ripe to be disrupted. This has potential to disrupt existing AI ecosystem and the way we do AI research.
SPEAKER:
Yaroslav Bulatov - Principal Researcher, Incept Labs
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 What comes after Deep Learning? | Incept Labs](https://i.ytimg.com/vi/jGy_GBkBj20/mqdefault.jpg)

![The Open Layer: How Open Models, Routing, and Inference Are Reshaping Agentic Engineering
[2026 - DAY 2 - CODING AGENTS] Closed frontier models get the headlines, but the agentic revolution is being built on something more flexible and more interesting: a hybrid stack of open-weight models, intelligent routing, and high-throughput inference infrastructure. In this panel, founders building the open AI ecosystem β from fine-tuned model deployment to multi-model orchestration to optimized routing and serving β get into what open actually means in 2026, and where it falls short.
Well dig into the real engineering tradeoffs: when open models win in agentic pipelines, when they dont, how routing and inference choices shape latency and cost at scale, and what it takes to build reliable agents in this open ecosystem as always-on agents become an increasingly core part of agentic engineering.
PANELISTS:
Chris Clark - Co-Founder & COO, OpenRouter
Dima Dzhulgakov - Co-Founder & CTO, Fireworks AI
Lucas Atkins - CTO, Arcee AI
Scott Breitenother - Co-founder & CEO, Kilo Code (moderator)
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 The Open Layer: How Open Models, Routing, and Inference Are Reshaping Agentic Engineering](https://i.ytimg.com/vi/jXyDdSTg7Qo/mqdefault.jpg)
![How to Build Your Own Model Router
[2025 - Day 3 - Lightning Talks] Tomas Kofman shares insights from building model routers that optimize LLM selection, exploring how to improve accuracy up to 25% while reducing costs up to 90% through intelligent routing methodologies. For engineers working with multi-model systems, this talk offers valuable perspectives on evaluation techniques and scalable implementation strategies to overcome common technical hurdles in deploying cost-effective, high-performance AI applications.
ABOUT THE SPEAKER:
Tomas Kofman, Co-Founder & CEO, Not Diamond -
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/ How to Build Your Own Model Router](https://i.ytimg.com/vi/ju7kKGVQRi0/mqdefault.jpg)