I build production-ready AI systems that solve real-world problems, combining deep learning, NLP, and full-stack deployment expertise.
I’m an AI/ML Engineer passionate about delivering AI products that are practical, intelligent, and fast. My focus is on end-to-end solutions—from model development to scalable deployment.
- 🎓 Education: B.Tech in Computer Science & Engineering (2022–2026) @ Babu Banarasi Das Institute of Technology and Management, Lucknow
- 💻 Problem Solving: Solved 500+ problems on LeetCode (DSA)
- 🚀 Goal: Bridging the gap between state-of-the-art AI research and production applications.
| Domain | Technologies & Tools |
|---|---|
| Generative AI / LLMs |     |
| Machine Learning |     |
| MLOps & Backend |     |
A conversational AI pipeline allowing users to chat with their PDF data instantly.
- Tech Stack: Python, LangChain, Llama-3.1 (Groq), FAISS, HuggingFace-Embeddings, Streamlit
- Key Achievement: Optimized retrieval using FAISS vector DB & local embeddings for sub-second search.
- Performance: Leveraged Groq LPU acceleration for high-speed inference and deployed via Hugging Face with Docker.
An intelligent recommendation engine utilizing Computer Vision for style matching.
- Tech Stack: Python, TensorFlow (ResNet50), Nearest Neighbors, FastAPI, Docker
- Key Achievement: Engineered a system achieving sub-second response times using Nearest Neighbors matching on ResNet50 extracted features.
- Impact: Reduced query latency by 30% via feature embedding caching. Deployed full stack on Hugging Face Spaces.
A real-time music recommendation system that detects your mood via webcam.
- Tech Stack: Python, OpenCV, CNNs, FastAPI, Streamlit, Spotify API
- Key Achievement: Trained a custom CNN for facial emotion classification and integrated the Spotify API for mood-matching.
- Method: Implemented Hybrid Collaborative & Content-Based Filtering to improve personalization.