👋 Hi, I'm Eugene Yan

I build recommendation systems and AI-powered experiences that serve customers at scale. Currently, I'm a Principal Applied Scientist at Amazon. Outside of work, I also...

Write, speak, and prototype on ideas in machine learning, RecSys, and LLMs.
Teach how to apply ML/LLMs effectively at ApplyingML.com & Applied-LLMs.org.
Send a newsletter about data, ML, and what I'm learning to 10,000+ subscribers.
In 2026 I'm learning: LLMs for security, memory and retrieval, human-agent collaboration.
Fun fact: I don't use the QWERTY keyboard (I use Dvorak instead).

📝 Recent Writing

Patterns for Building Cybersecurity Evals - Sun, 21 Jun 2026
Using LLMs to Secure Source Code - Wed, 27 May 2026
How to Work and Compound with AI - Sun, 03 May 2026
2025 Year in Review - Sun, 14 Dec 2025
Product Evals in Three Simple Steps - Sun, 23 Nov 2025

View the archives (212 posts) @ eugeneyan.com.

Pinned Loading

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

30.1k 4k
📝 Design doc template & examples for machine learning systems (requirements, methodology, implementation, etc.)

711 120
🤖 A prototype assistant for writing and thinking

Python 562 40
📰 Building News Agents to Summarize News with MCP, Q, and tmux

Python 331 40
🔍 Minimal examples of machine learning tests for implementation, behaviour, and performance.

Python 273 58
Semantic IDs: How to train an LLM-Recommender Hybrid with steerability and reasoning on recommendations.

Jupyter Notebook 139 33