Built from work this engineer published themselves. It makes no claim that they are available for hire, and it is marked noindex until they claim it. Source: eugeneyan.com. This is you, or it should not be here? Write to hello@aiengineer.me.
ai-engineer
Eugene Yan
Applied scientist; the patterns catalogue for LLM-based systems.
Applied scientist working on recommendation and search systems at Amazon, and author of long-form public writing on machine-learning system design. Patterns for Building LLM-based Systems & Products reads as a working checklist: evals, retrieval, caching, guardrails, defensive UX, and monitoring, each with the trade-off stated.
Technical stack & depth
Retrieval / RAG
Indexing, chunking, reranking, and grounding answers in a corpus.
Evaluation
Evals, traces, and a quality bar that is not a vibe check.
Production hardening
Latency, cost, observability, and the path from a notebook to a service.
Engineered solutions
- Write-upPatterns for Building LLM-based Systems & Productseugeneyan.com
Author of the patterns catalogue covering evals, retrieval, caching, guardrails, and monitoring.
- Portfoliogithub.com/eugeneyangithub.com
Open-source machine-learning system examples and applied write-up code.
Something here out of date or wrong? Write to hello@aiengineer.me and it will be corrected or removed.