Full Stack LLM Bootcamp
Production-grade engineering for large language models. Evals, retrieval, fine-tuning, and operational deployment.
What you'll learn
- Design reliable evaluation suites for generative systems
- Implement production retrieval-augmented generation pipelines
- Understand fine-tuning tradeoffs against prompt techniques
- Monitor, log, and secure production LLM APIs
About this course
An intensive curriculum created by Sergey Karayev, Charles Frye, and Josh Tobin on shipping real LLM products. It covers prompt engineering, evaluation harnesses, vector search, fine-tuning, and operational monitoring. Lecture videos and code notebooks are openly available on fullstackdeeplearning.com/llm-bootcamp. We are not affiliated with Full Stack Deep Learning.
Prerequisites
Comfortable with Python and deploying web services.