Eugene Yan
Applied Scientist, Amazon | Enterprise RAG & Recommendation Architect
Eugene Yan is an Applied Scientist at Amazon working at the intersection of machine learning systems, recommendation algorithms, and production LLM applications. His technical publications on RAG patterns, offline evaluation, and LLM design patterns are among the most cited practitioner resources in the industry.
Areas of focus
Professional niches
Proof of Work
Amazon: Scalable Model Serving Architecture & Latency Optimization
A production infrastructure blueprint developed by Eugene Yan at Amazon, implementing continuous batching, quantized weights, and horizontal autoscaling for high-concurrency model inference.
Deployment specifications are tailored to modern GPU cluster infrastructure; requires containerized execution runtimes.
Context: Optimized for high-throughput PyTorch / vLLM runtime serving.
View missionPatterns for Building LLM-based Systems & Products
Comprehensive reference manual documenting production patterns for evaluation, guardrails, retrieval-augmented generation, and fine-tuning with cost/latency trade-offs.
System design patterns; individual implementations must be profiled for specific latency constraints.
Context: Python, vector indexes, cross-encoders, and LLM evaluation frameworks.
View mission