I’ve built projects that span applied AI/ML and full‑stack engineering — from an end‑to‑end RAG summarizer and a scalable image classification API to real‑time face‑mask detection, a published flower‑recognition system, and a chess AI. Highlights include clean APIs, pragmatic UIs, and measurable results where possible.
An end-to-end Retrieval-Augmented Generation (RAG) application that allows users to upload documents and chat interactively with AI grounded in that context. It performs intelligent summarization, contextual Q&A, and insight extraction using LLMs with efficient vector retrieval for accuracy.
A scalable API built using FastAPI and PyTorch that provides REST endpoints for real-time image classification using fine-tuned deep learning models. It enables users to send images and receive class predictions with visual probability charts.
A computer vision application that uses deep learning and OpenCV to detect whether a person is wearing a mask in real time via a webcam feed. Designed for public safety monitoring and contactless compliance checks.
A published research project that uses Convolutional Neural Networks (CNNs) to classify and recognize flower species from both static images and real-time camera input. Built for use in botany, biodiversity, and educational applications.
A browser-based Chess AI application built using the Minimax algorithm with adjustable search depth, offering users an interactive chess-playing experience with visual interface and strategic move evaluation.
