Joydeep Medhi
AI/ML Scientist
Bengaluru, India
Specializing in Computer Vision, Generative AI, and Deep Learning solutions.
About Me
I am a Lead Data Scientist and Machine Learning Research Engineer based in Bengaluru, India, with a strong background in Computer Vision, Generative AI (LLMs, VLMs, RAG), and Deep Learning. With a B.Tech & M.Tech Dual Degree in Mathematics and Computing from IIT Delhi, I focus on developing innovative AI solutions for complex real-world problems.
My experience spans leading R&D initiatives at Lowe's Innovation Labs, driving significant revenue impact through AI-driven customer experience optimization, and developing core ML components for Mercedes-Benz R&D, including advanced driver-assistance systems (MBUX Interior Assistant) involving pose estimation, gesture recognition, and face authentication. I am passionate about pushing the boundaries of AI and translating research into tangible products.
Core Expertise
- Computer Vision
- Generative AI (GenAI)
- Large Language Models (LLM)
- Vision-Language Models (VLM)
- Retrieval-Augmented Generation (RAG)
- Deep Learning
- PyTorch
- TensorFlow
- Multi-Camera Tracking (MTMC)
- Pose Estimation
- Gesture Recognition
- Embedded AI
- AI Strategy & R&D
Education
B.Tech & M.Tech Dual Degree in Mathematics and Computing
Indian Institute of Technology Delhi (IITD)
2013 - 2018
Featured Experience
Lead Data Scientist - AI/ML
Leading R&D in CV & GenAI. Developed customer tracking systems ($1M+ revenue impact) & pioneered VLM/RAG solutions.
Senior ML Research Engineer
Developed core CV components for MBUX Interior Assistant (pose, gesture, tracking). Led Face Recognition module development.
Featured Project
Retail Shelf Empty Space Detection
Computer vision solution for detecting empty spaces in retail store shelves and racks. Helps optimize inventory management and improve restocking efficiency in retail environments.
Get In Touch
Interested in collaborating or learning more about my work? Feel free to reach out!