// ml

How I approach ML problems

ML work

AI Virtual Teaching Assistant

A retrieval-augmented question answering system for the IIT Madras Tools in Data Science course, built as a small RAG research lab. Embeddings are cached by content hash so trying a new retriever or reranker is cheap, and the same pipeline runs behind a FastAPI endpoint in Docker with tests and CI.

problem
Students need answers about a course that stay grounded in the course's own material.
approach
A modular pipeline where chunking, embeddings, retrieval (dense, BM25, hybrid), query transformation (HyDE, multi-query), RRF fusion, reranking and generation are each chosen by name in a YAML config; evaluation runs save their exact config and per-question results so a change can be measured.
  • RAG
  • NLP
  • Embeddings
  • ML Systems
ML work

PrivEx

A local privacy firewall that finds and redacts personal data (names, phone numbers, emails, card, bank and ID numbers, dates of birth, addresses, faces, spoken PII) in text, images, audio and video, entirely on your computer.

problem
Sensitive information hides in documents, images, audio and video, and often only contextually.
approach
A local engine with bundled OCR, face and speech models, a desktop app with human-in-the-loop review for images, and a Chrome extension that warns before personal data is pasted into a website. No LLM and no cloud calls.
  • Multimodal AI
  • Privacy
  • LLMs
  • Systems
ML work

MemBridge

A local-first personal AI memory with no mandatory cloud and no dependence on any provider's memory feature. Built for the FalkorDB hackathon; the write-up is linked below.

problem
An assistant's memory of you lives on someone else's servers, and you cannot read, correct or take it with you.
approach
Import ChatGPT or Claude history once, keep a provenance-linked, bi-temporal knowledge graph on your own machine (SQLite archive, FalkorDB graph, hybrid retrieval), and let MCP-capable assistants read and update it.
  • Memory
  • FalkorDB
  • MCP
  • Retrieval