Why RAG Is (Still) Not Dead: The Enduring Value of Retrieval in the Era of Expanding Context Windows
Every time a new Large Language Model debuts, the headlines follow a predictable pattern: “New Model with 1M Token Context!” Then come the hot takes: “RAG is Dead!” “No More Need for Retrieval!” “Just Dump All Your Data Into The Model!”
But if you’ve actually implemented AI systems that solve real business problems, you know that’s not how it w...
The Art of Interface Design: Making Good APIs that Scale
Why Well-Designed Interfaces Are Your Team’s Secret Weapon
As I’ve led engineering and data science teams across companies like Google, LinkedIn, and now as VP of Engineering & Data Science, I’ve observed a pattern: teams that invest in thoughtful interface design consistently outperform those that don’t. The most expensive technical debt i...
Beyond Algorithms: 3 Books That Shaped My AI Career (And Could Help Yours Too)
When I reflect on my journey in AI and machine learning, I notice a significant divide between what I learned in formal education and what actually proved valuable in the industry. While academic programs excel at teaching mathematical foundations and theoretical concepts, I’ve found that some of the most career-accelerating knowledge comes from...
Quality Assurance for AI
Traditional software quality assurance relies on predictable, deterministic behavior—the same input always produces the same output. But AI systems fundamentally break this assumption, creating a new challenge for quality assurance. This document outlines how to adapt QA practices for the AI era through effective evaluation and annotation system...
23 post articles, 6 pages.