Skip to content
View eugeneyan's full-sized avatar
πŸ‘¨β€πŸ’»
Learning. Building. Writing.
πŸ‘¨β€πŸ’»
Learning. Building. Writing.

Block or report eugeneyan

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
eugeneyan/README.md

πŸ‘‹ 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).

πŸ“ Recent Writing

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


Build README

Pinned Loading

  1. applied-ml applied-ml Public

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

    29.9k 4k

  2. ml-design-docs ml-design-docs Public

    πŸ“ Design doc template & examples for machine learning systems (requirements, methodology, implementation, etc.)

    706 120

  3. obsidian-copilot obsidian-copilot Public

    πŸ€– A prototype assistant for writing and thinking

    Python 562 40

  4. news-agents news-agents Public

    πŸ“° Building News Agents to Summarize News with MCP, Q, and tmux

    Python 319 38

  5. testing-ml testing-ml Public

    πŸ” Minimal examples of machine learning tests for implementation, behaviour, and performance.

    Python 271 58

  6. semantic-ids-llm semantic-ids-llm Public

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

    Jupyter Notebook 127 31