- 🌟 Over the past 5 years, I have specialized in AI and Machine Learning, building scalable solutions in production with expertise in computer vision, image & data analysis, autonomous systems, and GenAI, with robust backend development. I’ve worked with Fortune 500 companies, leading startups, including 3 years of work experience in the US. 🚀
- 🥇 Academics: Earned MS degree from the University of Minnesota, a top 25 US university, admitted with a 100% scholarship. Completed undergraduate degree at IIT Kharagpur, a top 5 university in India, ranking among the top 10% in the department.
- 📌 Technical Expertise: Designed and deployed AI systems with computer vision, image & data analysis, autonomous systems, reinforcement learning, and backend infrastructure alongside experience in LLMs and GenAI. Proficient in Python, C#/C++, TensorFlow/PyTorch, LangChain, Agents, OpenCV, ROS, and AirSim.
- 🌱 Research: Published 5 research papers, with 100+ citations as listed in Google Scholar 🏅
- 📧 I can be reached through email at subhodipsaha@gmail.com or connect in Linkedin
Description: This repo contains a wide range of custom functions & UI code for real-time detection & analysis of objects using YOLOv4
Tech Stack: OpenCV, Convolutional Neural Networks (CNNs), Pytorch, Computer Vision
Description: An end-to-end multi-agent system built with LangGraph that combines research and visualization capabilities
Tech Stack: Python, Streamlit, Langgraph, Multi-Agent, Tavily
Description: Flappy Bird game project in which a neural network has been trained to play Flappy Bird game by itself using reinforcement learning (RL)
Tech Stack: Reinforcement Learning, Python, C#, ML-Agents
Description: Created this MultiplayerVR social metaverse, similar to the popular Bigscreen VR app in VR headsets.
Tech Stack: Unity, C#, XR Interaction Toolkit, Photon Multiplayer