Train Custom Models with Fireworks & Langchain + SF Happy Hour ⭐

​Join Fireworks and LangChain August 25th for an exclusive hands-on workshop: get your hands on Fireworks and train a model yourself. Followed by a rooftop happy hour!

Evals are the foundation for all system improvements, but even with the right framework building these systems is challenging. Human-in-the-loop evaluations are costly and time intensive, while LLM as a judge systems can be unreliable and subject to bias. Build customized eval models for LangSmith that helps you scale your observability stack to optimize your AI application performance.

Who should join:

• ​AI/ML engineers and product builders shipping LLM or agent-based features who need a repeatable way to measure and improve performance

• ​Teams using (or evaluating) LangSmith who want hands-on guidance building a production-grade eval framework

• ​Anyone optimizing agent systems for reliability and cost, and looking to close the loop from evals into fine-tuning

• ​Builders curious about training or deploying Specialized Intelligence models on Fireworks using their own eval data as the foundation

​Agenda:

• ​5:00 – 5:30 PM: Welcome & Opening Remarks

• ​5:30 – 7:00 PM: Hands-On Workshop: Train, evaluate, deploy

• ​7:00 – 8:30 PM: Happy Hour: Food and drinks will be served

​*Location provided after registration approval

About us:
Fireworks is the platform for specialized intelligence, enabling companies such as Doximity, Revolut, and Shopify to train and serve models tailored to their own data, workflows, and use cases. Founded by the team behind PyTorch, and backed by AMD, Atreides, Benchmark Capital, Index Ventures, Lightspeed, NVIDIA, Sequoia Capital, and TCV, Fireworks provides hundreds of state-of-the-art open models in text, image, embedding, and multimodal formats globally.