Skip to content

AJAY VISHWANATHAN

Machine Learning Notes From Real Builds

I write about building ML systems in practice: architecture choices, debugging paths, trade-offs, and what actually works in production.

Recent Writing

Latest posts from the past 3 months.

  • You Can't Improve What You Don't Measure: Evaluating Knowledge-Grounded Retrieval Systems

    Published on:February 24, 2026
    7 min read

    After shipping a RAG retrieval system, the hardest question is whether it actually works. This post covers RAGAS, LLM-as-judge calibration, the evaluation triad, and how to build an eval pipeline that gives you real signal.

  • RAG in the Real World: Building a High-Precision Retrieval System for LLM Pipelines

    Published on:February 3, 2026
    8 min read

    Building a high-precision retrieval system sounds simple on paper. This is what actually happens when you ship one — the chunking failures, the retrieval gaps, and the hybrid search that finally gave us reliable signal.