Uploaded May 2025 | Updated November 2026, 1 hour ago
[2025 - Day 2 - MLOps & Platforms] Jonathan Jin shares insights from approaching model serving as a long-term ownership problem at Hinge, exploring how focusing on the "long tail" of model ownership creates sustainable AI platforms. Whether you're building model serving infrastructure or tackling observability challenges, this talk offers valuable perspectives on creating a "golden path" that empowers AI teams to innovate and scale their modeling investments without operational drag.
ABOUT THE SPEAKER:
Jonathan Jin, Staff Machine Learning Engineer, Hinge -
๐๏ธ GET YOUR TICKET TO AI COUNCIL 2026 ๐๏ธ
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.
โ aicouncil.com/sf-2026
โก FIND US:
X: https://x.com/AICouncilConf
LinkedIn: linkedin.com/company/aicouncilconf
Website: aicouncil.com
[2025 - Day 2 - MLOps & Platforms] Jonathan Jin shares insights from approaching model serving as a long-term ownership problem at Hinge, exploring how focusing on the "long tail" of model ownership creates sustainable AI platforms. Whether you're building model serving infrastructure or tackling observability challenges, this talk offers valuable perspectives on creating a "golden path" that empowers AI teams to innovate and scale their modeling investments without operational drag.
ABOUT THE SPEAKER:
Jonathan Jin, Staff Machine Learning Engineer, Hinge -
๐๏ธ GET YOUR TICKET TO AI COUNCIL 2026 ๐๏ธ
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.
โ aicouncil.com/sf-2026
โก FIND US:
X: https://x.com/AICouncilConf
LinkedIn: linkedin.com/company/aicouncilconf
Website: aicouncil.com
![Agents Break Data Security โ And Heres What You Do About It | Skyflow
[2026 - DAY 1 - WORKSHOP] AI Engineering teams are trying to secure AI systems built from components that didnt exist a year ago: agents, tools, memory, context graphs, orchestration frameworks. Traditional security wasnt built for any of this.
Here are 3 things practitioners are getting wrong right now:
- Agents are the new microservices
- Memory is where sensitive data goes to retire
- Your AI supply chain just got bigger than your software supply chain.
This session covers real architectures, real failure modes, and what runtime data control actually needs to look like when agents are making access decisions you never anticipated.
SPEAKER:
Amruta Moktali - Chief Product Officer, Skyflow
๐ 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 Break Data Security โ And Heres What You Do About It | Skyflow](https://i.ytimg.com/vi/Abh6CW0jvLQ/mqdefault.jpg)
![Context Engineering 2.0: Unifying MCP, Agentic RAG, and Memory | Redis
[2026 - DAY 2 - AI ENGINEERING] As AI systems move from single-shot chatbots to long-running, autonomous agents, the biggest bottleneck is no longer model capabilityโitโs context. Most production failures today stem from agents having the wrong information, at the wrong time, in the wrong shape. Prompt engineering and basic RAG pipelines were enough for early demos, but they collapse under real-world requirements like state, memory, structured data access, and safety.
This talk introduces Context Engineering 2.0: a systems-level approach to building agentic AI where context is treated as first-class infrastructure. Weโll explore why traditional RAG is insufficient on its own, why text-to-SQL and naive tool calling are brittle (and often dangerous), and why REST-style APIs are a poor abstraction for agent reasoning. From there, weโll examine three foundational pillars for modern agent systems: agentic RAG (retrieval that adapts to an agentโs plan), memory (short- and long-term, searchable and governed), and MCP-style semantic access layers that allow agents to safely explore and reason over structured data.
The core argument is simple but consequential: scalable agentic systems require a context engineโa unified layer that dynamically assembles state, memory, structured and unstructured data, and constraints into the modelโs working context. Attendees will leave with a clearer mental model for designing agent architectures that are more reliable, extensible, and aligned with how reasoning systems actually workโindependent of any specific framework or vendor.
SPEAKER:
Simba Khadder - Head of Context Engine, Redis & Founder of Featureform
๐ 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 Context Engineering 2.0: Unifying MCP, Agentic RAG, and Memory | Redis](https://i.ytimg.com/vi/AhKFNkgl760/mqdefault.jpg)
![Beyond the API: Modern Inference for Modern Workloads
[2026 - Day 2 - KEYNOTE] Practitioners from the companies at the frontier of inference and model development sit down to unpack what application developers need to understand right now: why fine-tuning is quietly resurging under the name RL, how smart teams are compressing inference costs by shaping smaller specialized models, who owns the model routing problem, and why inference capacity is structurally behind demand โ possibly for years.
PANELISTS:
Tuomas Rintamaki - Research Scientist, NVIDIA
Charles Zedlewski - Chief Product Officer, Together AI
Charles Frye - Member of Technical Staff, Modal
Bryan Bischof - Head of AI, Theory Ventures (Moderator)
๐ 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 Beyond the API: Modern Inference for Modern Workloads](https://i.ytimg.com/vi/B3axq9qPOVw/mqdefault.jpg)
![A SQL Based Metrics Layer for DuckDB and ClickHouse
[2025 - Day 2 - Analytics & BI] Mike Driscoll shares insights from building Rills SQL-based metrics layer using DuckDB, exploring how to aggregate raw data into summarized metrics and enable dimensional slicing through declarative SQL expressions. This talk offers valuable perspectives on implementing fast OLAP engines for real-time data access with sub-second response times, essential for analytics teams seeking to define metrics using familiar SQL dialect as part of a BI-as-code philosophy.
ABOUT THE SPEAKER:
Mike Driscoll, Co-Founder & CEO, Rill Data -
๐๏ธ GET YOUR TICKET TO AI COUNCIL 2026 ๐๏ธ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
โ https://aicouncil.com/sf-2026
โก FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ A SQL Based Metrics Layer for DuckDB and ClickHouse](https://i.ytimg.com/vi/B5jPz4xqQLg/mqdefault.jpg)

![How a Netflix Side Project Became the Universal Standard for Data Tables
[2025 - Day 1 - Data Eng & Infra] Ryan Blue shares insights from creating Apache Iceberg, exploring its origins at Netflix and evolution into a universal table format thats transforming the analytic database industry. This primer from Icebergs original creator offers valuable guidance on how these technologies are changing modern analytics and why theyre more relevant than ever today, making it essential viewing for anyone working with open table formats or building data lake architectures.
ABOUT THE SPEAKER:
Ryan Blue, Apache Iceberg Creator, Technical Staff, Databricks
๐๏ธ GET YOUR TICKET TO AI COUNCIL 2026 ๐๏ธ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
โ https://aicouncil.com/sf-2026
โก FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ How a Netflix Side Project Became the Universal Standard for Data Tables](https://i.ytimg.com/vi/BTwVhkQcg7g/mqdefault.jpg)
![The Deconstructed Database at Datadog
[2026 - DAY 1 - DATA ENG & DATABASES] Datadog has grown from a startup focused on infrastructure monitoring into a platform processing over a hundred trillion events daily.
Over the years, we expanded beyond metrics to include traces, logs, profiling, real user monitoring, and security. Our user base has broadened from operations to developers, analysts, and business users. More recently, automated agents have also become key consumers of our platform.
Our bottom-up culture encourages teams to take initiative. Consequently, we developed multiple specialized ingestion pipelines and query engines. These were built to satisfy strict real-time requirements and interactive experience, providing users with the insights necessary for success.
This focus on efficiency led to custom-built, proprietary solutions designed for our unique constraints. Today, however, the evolving landscape allows us to reconcile these specialized engines with open standards, blending the versatility of the ecosystem with our purpose-built designs.
In recent years, we have refactored the interfaces of these query engines to create a composable data system. This allows us to better leverage shared capabilities, enabling cross-dataset querying, advanced analytics, and more versatile access patterns. Our goal is to scale our bottom up culture. By defining clear contracts and high-level components, we enable decentralized decision-making. This improves performance, efficiency, and flexibility across the platform, while reducing silos.
By adopting a deconstructed stack, we combine the efficiency of the open-source ecosystem with our internal capabilities to build a truly composable system. This architecture provides the flexibility to adapt to immediate and future demands, specifically addressing requirements for scale, velocity, and operational resilience, while ensuring readiness for growing challenges such as data intensive operations like AI.
In this talk, we will discuss how we rely on and contribute to key projects in the data ecosystem: Arrow for data interchange, Substrait for plans, Calcite as an optimizer, DataFusion as an execution core, and Parquet for columnar storage.
SPEAKERS:
Julien Le Dem - Principal Engineer, Datadog
Pierre Lacave - Staff Engineer, Datadog
๐ 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 Deconstructed Database at Datadog](https://i.ytimg.com/vi/Bh9O20Q1dkE/mqdefault.jpg)
![Building SOTA Search: Itโs Ranking All the Way Down
[2025 - Day 3 - Lightning Talks] David Karam shares insights from building effective ranking systems with multi-dimensional functions that encode corpus topology and query streams, exploring how to merge signals like relevance, trustworthiness, and personalization at runtime. This talk offers valuable perspectives on recognizing emerging AI challenges as search problems in disguise, particularly relevant for engineers working on prompt optimization, ensemble selection, and reward modeling architectures inspired by decades of Google
Search work.
ABOUT THE SPEAKER:
David Karam, Co-Founder & CEO, Pi Labs -
๐๏ธ GET YOUR TICKET TO AI COUNCIL 2026 ๐๏ธ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
โ https://aicouncil.com/sf-2026
โก FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Building SOTA Search: Itโs Ranking All the Way Down](https://i.ytimg.com/vi/CLskAsoUgEc/mqdefault.jpg)

![The Deconstructed Database and the Advent of the Open Data Lake
[2025 - Day 3 - Keynote] Julien Le Dem shares insights from his years of experience building the deconstructed database vision, exploring how the big data ecosystem has evolved into a composable architecture organized around open source standards. This talk offers valuable guidance on leveraging interoperable components like Parquet, Arrow, and Iceberg to avoid vendor lock-in, particularly relevant for architects designing data systems or engineers building specialized query engines.
ABOUT THE SPEAKER:
Julien Le Dem, Principal Engineer, Datadog -
๐๏ธ GET YOUR TICKET TO AI COUNCIL 2026 ๐๏ธ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
โ https://aicouncil.com/sf-2026
โก FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ The Deconstructed Database and the Advent of the Open Data Lake](https://i.ytimg.com/vi/CqhkP2-0Js4/mqdefault.jpg)
![The Future of Data Engineering in the Agent Era
[2025 - Day 1 - Data Eng & Infra] Diptanu Gon Choudhury, Gleb Mezhanskiy, Nuno Campos, and Madison Faulkner share insights from revolutionizing data engineering through AI agents and foundation models, exploring advanced real-time processing and knowledge representation systems. This expert panel offers valuable perspectives on the evolution from traditional data modeling to dynamic knowledge graphs and graph RAG systems, particularly relevant for teams building context-aware data platforms or implementing agent memory systems.
ABOUT THE SPEAKERS:
Diptanu Gon Choudhury, Founder & CEO, Tensorlake
Gleb Mezhanskiy, Co-Founder & CEO, Datafold
Nuno Campos, Founding Engineer, Langchain
Madison Faulkner, Principal & Head of Data Science, NEA
๐๏ธ GET YOUR TICKET TO AI COUNCIL 2026 ๐๏ธ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
โ https://aicouncil.com/sf-2026
โก FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ The Future of Data Engineering in the Agent Era](https://i.ytimg.com/vi/D3fjQf_OiFg/mqdefault.jpg)