🎓 CS Student @ University of West London | AI & Data Engineering Intern (Jun – Sep 2026)

🔭 Built a GraphRAG + Hybrid RAG pipeline over enterprise clinical data at I/O Atelier, and a full-stack contract intelligence system for the construction industry at HaloRFP (AI B2B SaaS).

🏦 My work spans regulated industries — from Tier 1 banking to healthcare and construction — building production RAG systems that handle real, messy, large-scale data.

🧠 Obsessed with LLMs, knowledge graphs, vector search, and making AI systems actually work in production — not just demos.

⚡ I've processed 1.3B+ tokens at scale, built AWS serverless pipelines, and wrapped RAG engines as MCP servers with FastAPI.

🌱 Always learning — Pipeline orchestration, Project Management tools and whatever's broken in my pipeline this week.

📍 London, UK | Originally from Gujarat, India

💡 Long-term goal: build a large software company from the ground up.

⚠️ Note: My main projects — the GraphRAG clinical retrieval engine (I/O Atelier) and the contract intelligence platform (HaloRFP) — live in private company repositories under NDA. I document my internship work, learnings, and architecture write-ups publicly here → internship_documentation

📌 internship_documentation — Week-by-week documentation of my AI & Data Engineering internship work: GraphRAG pipeline design, retrieval evaluation, MCP servers, and lessons from production systems.

📌 aws-nhs-etl-pipeline — Serverless ETL pipeline on AWS processing 100,500 synthetic NHS records in under 2 seconds using S3, Lambda, IAM, Boto3, and CloudWatch.