
EigenTalk
A RAG-powered research assistant that turns uploaded documents into a searchable, conversational knowledge base — built in Next.js and TypeScript.
.../Projects...
A focused set: a RAG research assistant, real-time Angular dashboards, a Flask ML API, and Django automation — backend engineering, AI integration, and measurable outcomes.
.../Featured Projects...
A selection of my recent work

A RAG-powered research assistant that turns uploaded documents into a searchable, conversational knowledge base — built in Next.js and TypeScript.

Legacy Angular modernization and real-time air quality dashboards for Oizom Instruments — 12+ features shipped and several bugs resolved.
A Flask REST API backend serving two ML models — Naive Bayes crop recommendations and an Inception v3 disease detector (~87% accuracy) — consumed by a React frontend.
A Django automation system for large events: ingests Google Forms CSV data, generates QR-coded personalized invitations, and powers a real-time check-in dashboard.
These case studies are chosen for range across the stack rather than volume: a Next.js and TypeScript frontend wired to a RAG pipeline (EigenTalk), a legacy Angular modernisation with real-time geospatial dashboards (Envizom), a Flask REST API serving machine-learning models (Crop Element), and a Django automation system with QR-based check-in (Event Attendance Management System).
Every write-up follows the same structure — the problem, my role, implementation highlights, and outcomes — and links to the service it demonstrates, so the claims on the commercial pages stay tied to shipped work.
For the full picture of tools and depth, the skills page maps the stack domain by domain, and the experience page covers the roles where this work happened.