Hetansh Waghela
AI Engineer · RAG Systems · Mechanistic Interpretability · Applied ML
Mumbai, Maharashtra, India
Welcome!
I am a B.Tech student in Computer Science and Engineering (Data Science) at Dwarkadas J. Sanghvi College of Engineering, focused on building useful AI systems and studying how models behave internally.
My recent work spans production RAG, agentic systems, mechanistic interpretability, machine unlearning, biomedical AI, and compliance-grade retrieval. At AhumLabs, I built retrieval and assistant infrastructure for a multi-tenant trading platform, including tenant-specific knowledge ingestion, transaction indexing, and admin tooling for onboarding and form customization.
Outside internships, I build research and engineering projects such as ANVIL, MythForge, ImmunoPath, and Ghosts in the Model. I like projects that combine rigorous evaluation with systems that people can actually use.
news
| Jun 15, 2026 | Built ANVIL, a compliance-grade RAG system over ASME standards with auditable provenance and a 0.950 pass rate on a 100-example SPES-1 benchmark. |
|---|---|
| Jun 01, 2026 | Completed an AI Engineer internship at AhumLabs, building RAG and assistant infrastructure for tenant-specific trading workflows. |
| Feb 25, 2026 | Built ImmunoPath, a clinical decision-support pipeline for predicting immune biomarkers from routine H&E slides using MedGemma, TxGemma, Path Foundation, and MedSigLIP. |