Eugene Yan

Who is Eugene Yan?

Eugene Yan is an applied scientist at Amazon and a widely read writer on machine learning systems, production ML, and LLM patterns. He is best known for turning practical experience into clear, useful guidance for builders. (amazon.science)

Background and career

Yan studied psychology at Singapore Management University before moving into data science and machine learning roles. His path includes work at IBM, Lazada, a healthtech startup, and Amazon, where he has focused on recommendation systems, retrieval, ranking, and LLM-related work. (amazon.science)

He also publishes extensively through his personal site and Applying ML, where he shares posts, interviews, and field notes for practitioners. That writing has made him a familiar voice for teams trying to ship ML systems that work in production, not just in notebooks. (amazon.science)

Key facts about Eugene Yan include:

1. Current role: Senior Applied Scientist at Amazon.
2. Focus areas: ML, recommender systems, and LLM systems.
3. Background: Psychology training before moving into applied ML.
4. Public work: Personal writing, talks, and practitioner interviews.
5. Career path: IBM, Lazada, healthtech, then Amazon.

Notable contributions

1. Production ML writing: He has built a large audience by explaining ML systems and engineering patterns in plain language.
2. Amazon books recommendations: At Amazon, he has worked on systems that help readers discover books through recommendations and search. (amazon.science)
3. Applying ML: He runs a practitioner-focused site that curates papers, guides, and interviews for ML builders.
4. LLM system thinking: His current writing connects classic ML ops lessons to modern LLM workflows.
5. Career education: He frequently shares advice on communication, learning, and how to grow as an applied scientist.

Why they matter in AI today

1. Practicality: His work helps teams bridge the gap between research ideas and production systems.
2. Evaluation mindset: He emphasizes clear thinking about what to measure, review, and improve.
3. Systems perspective: His writing connects data, retrieval, ranking, and deployment into one stack.
4. Communication: He shows why good technical writing is part of building reliable AI.
5. LLM translation: He helps teams adapt proven ML habits to prompt- and agent-heavy workflows.

Where to follow their work

The best places to follow Eugene Yan are his personal site, his Applying ML site, and his Amazon Science profile. Those channels capture his writing, interviews, and current focus areas. (amazon.science)

He also shares talks and practitioner content through his public profiles and newsletters. If you want production-minded ML writing, his work is a strong reference point. (eugeneyan.kit.com)

How PromptLayer connects with Eugene Yan's work

Eugene Yan's focus on production ML, recommendation systems, and clear technical writing maps closely to how the PromptLayer team thinks about prompt management and LLM operations. Teams building with prompts, evaluations, and agent workflows can use PromptLayer to bring the same discipline to their own stack.

Ready to try it yourself? Sign up for PromptLayer and start managing your prompts in minutes.