Sourabh Gorkhe
AI • Computer Vision • ML Engineer
I am a B.Tech Computer Science graduate focused on building computer vision and deep learning systems. My work includes OCR pipelines, image processing workflows, neural networok and deep learning based inference applications, with an emphasis on practical problem-solving and research-oriented development.
AI & Computer Vision
Building safety-critical and intelligent perception systems using modern CV and ML.
- Object Detection (YOLO)
- OCR & Document Intelligence
- Autonomous Perception
- Video & Image Analytics
- image processing
Machine Learning
End-to-end ML pipelines from data to deployment.
- Supervised & Deep Learning
- Time-Series Forecasting
- Model Training & Evaluation
- Inference Pipelines
Tools & Systems
Practical tools that bridge theory, ML models, and real-world usage.
- FastAPI Backends
- Telegram Automation
- ML Dashboards
- System Integration
Projects
Telegram-Based Lecture Streaming Platform
Streams locally stored lecture videos via Telegram with a web interface.
Tech: FastAPI, Telethon, React, Tailwind
View on GitHub →YouTube & Twitter Video Downloader Bot
Robust media downloader with proxy, cookie, and cancellation support.
Tech: Python, yt-dlp, Telegram Bot API
View on GitHub →GRU-Based Traffic Prediction
Time-series traffic prediction system with real-time inference UI.
Tech: PyTorch, GRU, Streamlit
View on GitHub →Inter-LLM Orchestration Platform
Multi-agent AI communication system for reasoning research.
Tech: FastAPI, Modular Python
Skills
Ready to discuss your project? Multiple ways to reach me
Quick Start
To get started quickly, reach out with the following:
What challenge are you solving? (CV, ML, OCR, automation, etc.)
Model, report, prototype, dashboard, or research support.
Deadline, data availability, compute or scope constraints.
I typically respond within 24 hours with a clear next-step plan. Open to research, internships, and collaboration.