Chirag Vijay — AI/ML Engineer

AI ENGINEER

Chirag Vijay

I build AI that survives real users.

See work→Say hiAvailable

I make machines that read, think, and (mostly) tell the truth.

§01

Selected work

Lexora

RAG-based legal research assistant for Indian law.

FastAPI
BGE embeddings
cross-encoder rerank
RAGAS

V1 liveCase study →

DocLayout-YOLO

Fine-tuned YOLOv8 that detects a document page's semantic layout and extracts its text.

YOLOv8 (fine-tuned)
ONNX Runtime
PaddleOCR
OpenCV

MIT · v1.0.0Case study →

Systems I've built and evaluated end to end — each with the architecture and the real numbers behind it.

§02

Writing

I Built a Production RAG System for Indian Law — and Refused to Trust It Until I Measured ItAug 14, 2026

§03

About & contact

I build AI systems that have to survive real users, not just a demo. Lately that means retrieval pipelines that cite their sources (Lexora) and vision models that turn messy documents into clean, structured data (DocLayout-YOLO). I like the unglamorous parts — evals, latency, the numbers that decide whether a model actually works. Currently an AI/ML Engineer at TCS iON.

CORE STACK

Python
LangChain
FastAPI
Azure OpenAI
ChromaDB
Docker

Available for full-time roles