Vinay C.

Open to Staff and Principal GenAI engineering roles

The hard part of AI isn't the model. It's everything around it.

I'm Vinay, a Staff Software Engineer at Intuit with 14 years across five companies. I build the evaluation harnesses, golden datasets, retrieval and guardrails that make generative and agentic AI trustworthy in production.

Download résuméMessage me on LinkedInCase studies →

IntuitMicrosoftDocusignOracleSAP

14yrs

shipping distributed systems and AI

25M+

monthly users on the AI products I led at Microsoft

4M+

GenAI datapoints evaluated a year at Intuit

1

granted patent: data privacy as a cloud service

Selected work

All case studies →

Intuit · Staff SWE · 2026

GenAI regression evaluation

A RAG stack shipped changes with no way to see if retrieval regressed. I built a golden dataset from real customer utterances, daily automated runs, embedding-model evals (BGE-M3, Stella) and per-query MRR / mAP / hit-rate explainability.

4M+ datapoints / yr, run daily

Microsoft · Senior SWE · 2024–25

Generative AI in the Power Platform

Led generative and agentic AI work reimagining Power Apps and Power Pages: AI in the authoring experience, holding the bar on performance and availability for a massive install base.

2 flagship products · 25M+ MAU

Oracle · Principal MTS · 2022–24

Modernizing Enterprise Manager

Headed the modernization of a 30-year-old product with 10K+ live customers, shaping design, strategy and roadmap with Senior Directors.

+40% efficiency · +20% engagement · +25% satisfaction

Models are commodities. Judgment is not.

The advantage was never the LLM you picked. It's the eval harness, the golden datasets, and the guardrails that tell you — reliably, daily — when the system is wrong.

How I think

All 38 notes →

The Handbook

GenAI engineering, from RAG to production agents

Short lessons on retrieval, evaluation, agents and system design trade-offs, each ending with the line I'd say in a design review.

Open the handbook →
Agents & Frameworks

What is an AI harness, and why does it matter more than your model choice

For a while, I thought picking an AI product came down to one question: which model is underneath? GPT, Claude, Gemini. Smarter model, better product. It seeme…

RAG & Retrieval

RAGA Framework, Part 1: Why and how can you evaluate your LLM App?

Part 1 of a series on evaluating LLM apps with Ragas.

Agents & Frameworks

10 AI Agent Design Patterns Every AI Engineer Should Know

LangGraph. CrewAI. AutoGen. OpenAI Agents SDK.

Latest from the notebook

All notes →
LLM Fundamentals

I Finally Understood Self-Attention. Here’s How Transformers Actually Work.

October 17, 20265 min read
RAG & Retrieval

RAGA Framework, Part 7: Beyond RAG: Evaluating AI Agents with Ragas

August 5, 20266 min read
RAG & Retrieval

RAGA Framework, Part 6: Who Evaluates the Evaluator? The Limits of LLM-Based Metrics

July 30, 20265 min read
RAG & Retrieval

RAGA Framework, Part 5: How to Fix a RAG Pipeline Using Evaluation Results

July 29, 20265 min read

Hiring for GenAI? Let's talk.

Open to Staff and Principal GenAI engineering roles, based in Bengaluru. The fastest way to reach me is a LinkedIn message; the résumé has the full history.

Message me on LinkedIn →Résumé