​Building the AI Stack: Models, Infrastructure, Inference, Agents & Graphs

​Official side event of AI Engineer Paris, 2026

​AI engineering is moving beyond individual models toward full-stack systems that bring together models, inference, data, and infrastructure. Join Mistral, Neo4j, Daytona, and SGLang for an evening of practical conversations about what it takes to build and run modern AI applications.

​We’ll explore the technologies powering the AI stack—from open models and high-performance inference to to secure sandbox infrastructure for AI agents and graph-powered context. Speakers will share real-world approaches, lessons learned, and emerging patterns for building AI applications that are faster, more capable, and easier to develop.

​Come hear from the teams building the infrastructure and developer tools behind the next generation of AI—and stick around to connect with other AI engineers, developers, and builders.

​Featuring: Mistral · Neo4j · Daytona · SGLang

​What we’ll cover:

• ​Building with open and efficient AI models

• ​High-performance inference and serving with SGLang

• ​Secure, scalable infrastructure for AI agents with Daytona

• ​Using graphs to give AI applications richer context and memory

• ​Practical patterns for bringing these pieces together in production

​​Agenda

​​​​​​🕒 6:30 pm – 7:00 pm
Welcome Gathering and Opening Remarks

​🎤 Organizers

​​​​​​​​🕒 7:00 pm – 7:15 pm
Talk "Agent Memory and Context Graph "​

​🎤 Henry Collie, Neo4j

​​​​​​​​​Outline:

​How do you give AI agents the memory and context they need to do more than just answer the next prompt? We’ll look at how agent memory and Context Graphs connect past interactions, decisions, and relationships so agents can use context to reason, learn, and make better decisions over time.

​​🕒 7:15 pm – 7:30 pm
Talk "Own your agent"

​🎤 Joffrey Thomas, Mistral AI

​​​​​​​​Outline:

​As we transition from conversational chatbots to autonomous agents, relying on closed-source APIs has become a major bottleneck for production-grade applications. To build reliable agents that handle critical tasks, developers need absolute control over their models, their data, and their infrastructure. In this talk, we will discover why Open Source is the only viable foundation for truly autonomous agents, offering the freedom to customize, the power to secure your data, and the independence to build without boundaries.

​​🕒 7:30 pm – 7:45 pm
Talk "Deep Diving Speculative Decoding In SGLang"

​🎤 Alex Nails, SGLang

​​​​​​​​Outline:

​Together, we go over the latest in SGLang's architecture for Speculative Decoding. This will include a brief overview of the basics for each major speculative decoding method, the current state of each in SGLang, and the next infrastructure directions for best utilizing speculative decoding.

​​🕒 7:45 pm – 8:00 pm
Talk "Give the Model a Computer: The One Thing Every AI Agent Framework Agrees On"​

​🎤 Mislav Ivanda, DevEx Engineer at Daytona

​​​​​​​​​Outline:

​Building an agent is easy. Deciding where its code runs is the part that follows you to production.

​This talk comes from a year of building Daytona integrations across the agent ecosystem: LangChain, CrewAI, Google ADK, Mastra, Pydantic AI, the OpenAI Agents SDK, and a long tail behind them. Integration after integration, the same pattern kept surfacing. Frameworks that agree on nothing, not even the language, not the mental model, not who controls the flow, all converge on one identical primitive: give the model a computer. We'll trace why.

​Every framework ends up facing the same question: where does the model's code actually run? Only three answers exist, and two of them stop holding once real users show up. That's why the past year went the way it did, with frameworks deleting their own code interpreters rather than defending defaults they couldn't. And that's why the computer keeps growing: first a tool call, then the place the agent lives, then a thousand machines at once.

​You'll leave with one rule: pick the boundary before the framework. Frameworks are opinions. The boundary is a commitment.

​​​​​​​​​​​​​​​​🕒 8:00 pm - 9:30 pm

​​​Networking

​With pizzas and beverages

​About event

​This is dynamic gathering for AI enthusiasts, innovators, and professionals to collaborate, share ideas, and explore the latest advancements in artificial intelligence. Whether you're building AI products, researching cutting-edge algorithms, or simply passionate about the field, join us to connect, learn, and drive the future of AI forward.