Skip to content
View adumrewal's full-sized avatar
🔮
In the quest for knowledge and making it more accessible for others.
🔮
In the quest for knowledge and making it more accessible for others.

Block or report adumrewal

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
adumrewal/README.md

Hello | Hola | Bonjour | Hallo | नमस्ते | 你好 | مرحبا 🧑‍💻👋

  • 💡 I'm here to share practical implementations, best practices, and insights from my journey in AI, machine learning, and software engineering.
  • 🔭 I specialize in AI product development from ideation to production, with focus on scalability and customer value.
  • 🎓 IIT Madras, CSE | TU München | Microsoft | IBM Research

GitHub Stats 📊

Contributions 📈

  • Over 500 contributions 🚀 in the past year across 25+ repositories.
  • Open-source projects, including Hugging Face, YOLOv5, SIFT Image Similarity, and Deep Image Matting.
  • Led multiple high-impact projects at 56 Secure and Microsoft.
  • Built for the community at Schmooze: Meme-Based Dating App and CitiCafe.

Highlighted Projects 📋

  • SIFT Image Similarity: An interactive Python implementation of the SIFT algorithm for image similarity. ⭐ 180+ stars
  • Deep Image Matting: Simplified deep image matting training with TensorFlow and Keras. 🚀 40+ stars
  • Production Python Server: A production-ready server leveraging Elastic APM, Docker, and Flask. 🔧🌎
  • Adaptive Cards: Open exchange format enabling developers to exchange consistent UI content. ✨ 1.7k+ stars
  • YoloV5: State-of-the-art and most used object detection model with PyTorch. ⬇️ 47M+ downloads

Achievements 🏆

  • Lead Engineer for AI-based Video and Location Surveillance products (200M+ image, 3B+ location data points).
  • Scaled Microsoft Teams features to 20M MAU, leading UI automation and growth.
  • Recognized by ACM IUI and ACM CoDS for pioneering research in AI/NLP and citizen engagement.

💼 Have questions or just want to chat? Feel free to reach out anytime at:

  • Email: amoldumrewal [at] gmail [dot] com
  • LinkedIn: Amol Dumrewal

Pinned Loading

  1. microsoft/AdaptiveCards microsoft/AdaptiveCards Public

    A new way for developers to exchange card content in a common and consistent way.

    C# 1.8k 556

  2. SIFTImageSimilarity SIFTImageSimilarity Public

    Interactive code for image similarity using SIFT algorithm

    Python 190 40

  3. imageMatting imageMatting Public

    Simplified Deep Image Matting training code with keras on tensorflow

    Python 41 6

  4. llm-api-gateway llm-api-gateway Public

    Gateway to control LLM API/SDK calls. Supports access to OpenAI, Azure, Anthropic and Bedrock calls

    Python 1

  5. python-production-server python-production-server Public template

    A boiler plate python production server using elasticsearch, elasticAPM, Docker and flask. Modular code with all the necessary code for setup and easily configurable based on usecase.

    Python 7 3

  6. mtcnn-landmark-detector mtcnn-landmark-detector Public

    Facial Landmark detector - eyes, nose, mouth (CPU compute optimised, IoT capable)

    Python 6