Uploaded May 2025 | Updated November 2026, 8 minutes ago
[2025 - Day 2 - Foundation Models] Ravin Kumar shares insights from his perspective across building products, training foundation models, and daily GenAI usage, exploring how to approach LLMs as practical tools rather than getting caught up in the hype. For practitioners new to GenAI or looking to ground their approach in realistic expectations, this talk offers valuable guidance on starting with a practical foundation before exploring the more exciting aspects of this transformative technology.
ABOUT THE SPEAKER:
Ravin Kumar, Senior Researcher, Google DeepMind -
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 2 - Foundation Models] Ravin Kumar shares insights from his perspective across building products, training foundation models, and daily GenAI usage, exploring how to approach LLMs as practical tools rather than getting caught up in the hype. For practitioners new to GenAI or looking to ground their approach in realistic expectations, this talk offers valuable guidance on starting with a practical foundation before exploring the more exciting aspects of this transformative technology.
ABOUT THE SPEAKER:
Ravin Kumar, Senior Researcher, Google DeepMind -
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
![Introducing Pixeltable: Open Source Data Infrastructure for Multimodal AI
[2025 - Day 2 - MLOps & Platforms] Marcel Kornacker shares insights from building Pixeltable, an open-source AI data infrastructure with a declarative, incremental approach for multimodal workloads. Whether youre juggling multiple specialized systems or seeking to simplify AI data complexity, this technical deep-dive from the founder of Apache Impala and co-founder of Apache Parquet offers valuable perspectives on bringing together data, computation, and models through unified infrastructure.
ABOUT THE SPEAKER:
Marcel Kornacker, Co-Founder & CTO, Pixeltable -
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/ Introducing Pixeltable: Open Source Data Infrastructure for Multimodal AI](https://i.ytimg.com/vi/R8eFWd0qjds/mqdefault.jpg)
![A Local-First Approach to Extremely Fast Streaming Visualization
[2025 - Day 1 - Workshops] Parham Parvizi shares insights from local-first data visualization approaches, exploring how WebAssembly and in-browser computation achieve high-performance analytics while reducing cloud costs. This workshop offers valuable perspectives on building browser-native analytics dashboards, connecting real-time data streams, and leveraging Perspectives API across multiple languages, essential for teams seeking cost-efficient, scalable visualization solutions without server-side complexity.
ABOUT THE SPEAKER:
Parham Parvizi, Founding Data Architect, Prospective -
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/ A Local-First Approach to Extremely Fast Streaming Visualization](https://i.ytimg.com/vi/S5upxdqT76Y/mqdefault.jpg)

![After the Lakehouse: Building Data Infra for the AI Era
[2026 - Day 2 - KEYNOTE] The lakehouse architecture solved a real problem β but AI has rewritten the requirements. Latency, compute separation, vector workloads, real-time inference pipelines: the demands look nothing like they did five years ago. Three engineers who helped build the modern data stack join us to debate whats actually changing under the hood, whats being thrown out, and what the next five years look like for the teams who have to ship on top of it.
PANELISTS:
Yury Izrailevsky - Co-founder & President, ClickHouse
Nikita Shamgunov - VP of Engineering, Databricks
Carl Perry - Head of Analytics, Snowflake
Jamin Ball - Partner, Altimeter (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 After the Lakehouse: Building Data Infra for the AI Era](https://i.ytimg.com/vi/S_RIbZU5seE/mqdefault.jpg)
![AI Cram Session
[2025 - Day 1 - AI Engineering] Rachel Lee Nabors shares insights from demystifying machine learning concepts, exploring the real meaning behind acronyms like RAG and the mathematics underlying deep learning through colorful illustrations and metaphors. This talk offers valuable perspectives for newcomers to the field, providing essential concepts, mental models, and glossary terms needed to understand machine learning, presented by the cartoonist behind educational tools like react.dev.
ABOUT THE SPEAKER:
Rachel Lee Nabors, Former React Core, Meta -
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/ AI Cram Session](https://i.ytimg.com/vi/SdDuVwfmwo0/mqdefault.jpg)
![Agents Are Eating the Semantic Layer | Zenlytic
[2026 - DAY 2 - ANALYTICS & DATA SCI] When LLMs first hit the scene, the consensus was clear: you need a semantic layer for reliable, accurate results. The benchmarks proved it. The research confirmed it. I believed it too (and was one of the first voices saying so).
Then the models got better. And the consensus stopped being true.
Today, a semantic layer doesnt give your agent accuracy. It gives your agent a ceiling. It limits flexibility, constrains the questions your agent can answer, and forces you to anticipate every question in advance. Thats not how data in enterprises actually works.
This talk covers where the semantic layer falls short, what we built instead, and how to architect agents that gather and create business context dynamically, without sacrificing governance or trust.
SPEAKER:
Paul Blankley - CTO & Co-founder, Zenlytic
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 Agents Are Eating the Semantic Layer | Zenlytic](https://i.ytimg.com/vi/Sm5x2ItO5os/mqdefault.jpg)
![AI Launchpad 2025: Tower
[2025 - Day 1 - AI Launchpad] Serhii Sokolenko and Brad Heller share insights from Towers elegant 2-layer data stack where all compute engines coexist harmoniously, exploring how to run Python frameworks from ETL to inference on scalable single-node compute with Iceberg open storage. These Snowflake alumni and Big Tech veterans offer valuable perspectives on building simple yet powerful architectures that enable seamless collaboration between different processing engines without complexity overhead.
ABOUT THE SPEAKERS:
Serhii Sokolenko, Co-Founder & CEO, Tower
Brad Heller, Co-Founder & CTO, Tower -
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/ AI Launchpad 2025: Tower](https://i.ytimg.com/vi/TZ7cdlGk12A/mqdefault.jpg)
![Python Over Data Lakes: Declarative Environments, Data Management & Other Things w/ Feathers
[2025 - Day 1 - Data Science & Algos] Ciro Greco shares insights from designing reproducible data workloads over Data Lakes, exploring how to decouple code, compute, and data management for deterministic pipeline reproduction. For engineers developing Python data pipelines or debugging complex workflows, this talk offers valuable perspectives on leveraging open-source components like Iceberg, Arrow, and Docker to create declarative functional DAGs with efficient cloud execution.
ABOUT THE SPEAKER:
Ciro Greco, Founder, Bauplan -
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/ Python Over Data Lakes: Declarative Environments, Data Management & Other Things w/ Feathers](https://i.ytimg.com/vi/T_iCmy8U4fo/mqdefault.jpg)
![When Your AI Agent Runs for 16 Days Straight | Factory
[2026 - DAY 2 - CODING AGENTS] Most AI coding agents top out at short, interactive sessions - a few minutes of back-and-forth before context degrades. At Factory, we built a system that sustains autonomous software development for hours, days, and even weeks. An orchestrator decomposes large projects into features, spawns focused workers with clean context, coordinates through git, and validates at every milestone. This talk covers the architecture behind multi-day agentic workloads: managing context limits, multi-model orchestration, balancing serial reliability with parallel speed. We also share production data on what actually changes when agents shift from 8-minute conversations to 16-day autonomous runs.
SPEAKER:
Eno Reyes - CTO, Factory
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 When Your AI Agent Runs for 16 Days Straight | Factory](https://i.ytimg.com/vi/UKDE2_IBk7A/mqdefault.jpg)
![What It Takes to Build Reliable AI Systems for Production Operations | Resolve AI
[2026 - DAY 3 - APPLIED AI] As AI systems move from assisting engineers to taking action across production workflows, the technical bar rises fast. Real-world environments are noisy, fragmented, and high-stakes, making reliability, context, and control core design problems rather than afterthoughts.
In this talk, Steven Karis, Chief Architect at Resolve AI, will share practical lessons from building AI systems that operate across incidents, debugging, and daily production operations. He will cover the architectural patterns required to make these systems useful in practice, including context aggregation across fragmented tools, coordinated reasoning and planning, and enforcement of safe action boundaries in complex environments. The session will also explore a broader industry shift: engineers are moving from being direct operators to supervisors who define policy, review decisions, and manage exceptions. The goal is not just to make AI more capable, but to make it dependable for engineers to collaborate with and delegate to.
SPEAKER:
Steven Karis - Chief Architect, Resolve AI
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 It Takes to Build Reliable AI Systems for Production Operations | Resolve AI](https://i.ytimg.com/vi/USe4fZk1mag/mqdefault.jpg)
![Welcome to Our Data Benchmark, Where Everythings Made Up and the Points Dont Matter
[2026 - DAY 2 - ANALYTICS & DATA SCI] SPIDER, DSBench, and every other analytics benchmark treat data work like a pub quiz: heres a question, heres the answer, did you match? But real analytics is arguing about whether revenue means bookings or collections, discovering that Stripe amounts are in cents while your platform stores dollars, and figuring out why the numbers dont tie to last quarters deck. Current benchmarks cant express any of thatβthey just check if you got 47.3. Worse: smarter models keep making the same mistakes. Opus is clearly more intelligent than Sonnet, but it falls into the same trapsβpath of least resistance, accepts the first answer, doesnt ask clarifying questions. Well show specific examples where industry standard benchmarks fail (including our own) and share some ideas for evals that test what analysts actually do: learn a messy warehouse over time, not answer a frozen question on day zero.
SPEAKER:
Izzy Miller - AI Engineer & AI Research Lead, Hex
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 Welcome to Our Data Benchmark, Where Everythings Made Up and the Points Dont Matter](https://i.ytimg.com/vi/UwqyN-6tPKo/mqdefault.jpg)