Eugene Yan
“Eugene Yan” delves into the intricacies of architecting enterprise-level systems with a focus on knowledge base infrastructure, generative AI, and data augmentation for machine learning. The content explores the challenges of static data in a dynamic world, the importance of understanding over indexing, and the necessity of contextual precision in AI applications. By leveraging technologies like Spark, EMR on EKS, Airflow 3, and vector embeddings, the document emphasizes the need for fault-tolerant, secure, and responsive systems that go beyond traditional approaches to data processing and analysis.
2025 Year in Review
An eventful year of progress in health and career, while making time for travel and reflection.
📚 Read more at Eugene Yan🔎 Find similar documents
Product Evals in Three Simple Steps
Label some data, align LLM-evaluators, and run the eval harness with each change.
📚 Read more at Eugene Yan🔎 Find similar documents
Advice for New Principal Tech ICs (i.e., Notes to Myself)
Based on what I've learned from role models and mentors in Amazon
📚 Read more at Eugene Yan🔎 Find similar documents
How to Train an LLM-Recommender Hybrid that Speaks English & Item IDs
Semantic IDs and the convergence of recsys, search, and chat.
📚 Read more at Eugene Yan🔎 Find similar documents
Evals for Long-Context Question & Answer Systems
Key metrics, creating datasets, eval methodology, and example benchmarks.
📚 Read more at Eugene Yan🔎 Find similar documents
AI Engineer 2025 - Improving RecSys & Search with LLM techniques
Recsys & search are converging with LLMs via semantic IDs, data augmentation, and unified foundation models.
📚 Read more at Eugene Yan🔎 Find similar documents
Qualities and Behaviors of Exceptional Leaders
What makes a good leader? What do good leaders do? And wartime vs. peacetime leaders.
📚 Read more at Eugene Yan🔎 Find similar documents
Building News Agents with MCP, Amazon Q CLI, and tmux
Automating my daily news flash via agentic workflows with Amazon Q CLI and MCPs
📚 Read more at Eugene Yan🔎 Find similar documents
Stop Blaming the LLM-as-Judge; Fix Your Process Instead
Applying the scientific method, building via eval-driven development, and monitoring AI output.
📚 Read more at Eugene Yan🔎 Find similar documents
Frequently Asked Questions On My Writing Process
How I started, why I write, who I write for, how I write, and more.
📚 Read more at Eugene Yan🔎 Find similar documents
Frequently Asked Questions about My Writing Process
How I started, why I write, who I write for, how I write, and more.
📚 Read more at Eugene Yan🔎 Find similar documents
NVIDIA GTC - Building LLM-Powered Applications
Chip Huyen and I share what we've learned, best practices, and insights at NVIDIA GTC 2025.
📚 Read more at Eugene Yan🔎 Find similar documents