Build smarter, faster—AI developer tools engineer AI into reality

Dive into the ecosystem of SDKs, frameworks, orchestration libraries, and tracking tools that empower AI developers. This track explores the platforms, protocols, and best practices that make AI development reproducible, modular, and production-ready

AI Developer Tools

Learn from Industry Leaders about:

  • Frameworks and SDKs for building and deploying AI models.
  • Orchestration libraries like LangChain for managing complex multi-agent workflows.
  • Using the MCP protocol to structure context in GenAI systems.
  • Tools for experiment tracking, versioning and reproducibility.
  • Best practices for interationg APIs and deploying modular AI pipelines.

Track Speakers London 2025

Track Speakers San Diego 2025

San Diego's program will go live soon! Until then, please take a look at

New York's 2024 Program!

Track Speakers Munich 2025

Track Speakers New York 2025

Track Speakers Berlin 2025

Track Program London 2025

Track Highlights San Diego 2025

Track Progrm Munich 2025

Track Program New York 2025

Track Program Berlin 2025

Track Sessions MLCon New York

Track Sessions MLCon New York

View all sessions

Track Sessions MLcon Berlin 2025

Track Sessions MLcon Berlin 2025

View all sessions

Track Sessions London 2025

Track Sessions London 2025

View all sessions

Track Sessions San Diego 2025

Track Sessions San Diego 2025

View all sessions

Track Sessions MLcon Munich 2025

Track Sessions MLcon Munich 2025

View all sessions

Frequently Asked Questions

What is the focus of the AI Developer Tools track?

This track showcases the essential tools developers need to bring AI projects from prototype to production. Topics include orchestration frameworks, SDKs, tracking systems, and integration strategies for scalable AI workflows.

What frameworks and SDKs are covered?

Attendees will explore SDKs in Python and full-stack ML frameworks such as TensorFlow, PyTorch Lightning, and Hugging Face Transformers, with an emphasis on reproducibility, modularity, and API integration.

How do orchestration libraries support AI development?

Orchestration tools like LangChain and Guidance help developers manage prompts, memory, and logic flow across multi-agent or multi-model pipelines. This enables structured execution and fine-grained control of AI behavior.

What is MCP and why does it matter for developers?

The Multi-Agent Communication Protocol (MCP) provides a standard for secure and structured context sharing across LLM agents. This supports agent collaboration and transparency in complex GenAI applications.

How can experiment tracking tools enhance AI workflows?

Tools like MLflow, Weights & Biases, and Neptune help teams log experiments, manage model versions, and compare performance metrics—ensuring consistency across development cycles.

Behind the Tracks