Here are some of the projects I've worked on. Most are written either to solve my own problems or just for the fun of building things. Check out my GitHub for more.
Showing 3 projects
Designing a full-stack, LLM-powered digital twin that learns an individual's writing style from email history and generates emails in their voice using a modular feature-training-inference pipeline.
CattleLens is a full-stack AI cattle-care platform that classifies eight cattle breeds from uploaded images using a ResNet-18 model trained on an imbalanced dataset with class weighting and staged fine-tuning. It combines a FastAPI and PyTorch inference backend with JWT authentication, prediction history, cattle profiles, diet plans, and vaccination record management. The app uses SQLite locally, PostgreSQL in production, Alembic-managed database migrations, and a CPU-ready Docker container.
A running collection of research paper implementations where I break down the intuition, mathematics, and code behind important ML and deep learning ideas.
