About
I'm a computer science student at Bennett University (B.Tech, class of 2027) working on applied AI. I'm currently an AI Intern at HERE Technologies and a Google Summer of Code '26 contributor at AOSSIE, where I work on PictoPy, a privacy-first gallery manager for desktop. Previously, I compressed LeNet-5 in C++ for FPGA inference as a Machine Learning Intern at KeenSemi, and I served as Head of Tech and then Vice Chairperson of the Data Science Society at Bennett. I build in public.
Work Experience
Education
Skills
Check out my latest work
I've worked on a variety of projects, from simple websites to complex web applications. Here are a few of my favorites.
A fully offline, privacy-first desktop image gallery by AOSSIE. It groups faces across your library, tags photos with detected objects, and supports semantic search, all with on-device AI models. As a contributor and GSoC 2026 participant, I worked on ML pipelines, CI/CD, face clustering and Visual Semantic Intelligence.
A real-time Automatic Braking System pipeline merging object detection and lane segmentation under 1.1GB of VRAM. Decouples PyTorch and ONNX Runtime execution environments to optimize GPU use, reaching under 30ms inference and 20 FPS across two neural networks.
An AI-powered infant care tracking application with text and voice support and responses in under 5 seconds. Uses a Retrieval-Augmented Generation pipeline on a local Gemma model, indexing 10,000+ WHO guidelines, pediatric care documents and infant health records to reduce hallucinated responses by 60%.
@AOSSIE-Org
@meshery
@sugarlabs
@activist-org
@ohcnetwork
@thedesignnetwork
@dss-bu