Moamen Abdelrazek

Montreal, Quebec, Canada
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
Moamen Abdelrazek is an AI Engineering Manager based in Montreal with 10 years of experience building production-grade machine learning systems across NLP and computer vision. He has led teams at RBC and now SETS, bringing research rigor to industry—evidenced by 8+ papers at top ML venues like NeurIPS and CVPR—while shipping practical solutions that prioritize user impact. Hands-on in PyTorch, he maintains a scalable project template used for segmentation, classification, GANs and RL, and has contributed model integrations and training improvements such as ERFNet weighted loss support. A competitive programmer who values clean code, Moamen bridges cutting-edge research and reliable deployment, ensuring models not only perform in benchmarks but delight customers in daily use.
code11 years of coding experience
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
1answer
0questions
github-logo-circle

Github Skills (6)

semantic-segmentation10
pytorch10
machine-learning10
deep-learning10
python10
dqn8

Programming languages (1)

Python

Github contributions (5)

github-logo-circle
A scalable template for PyTorch projects, with examples in Image Segmentation, Object classification, GANs and Reinforcement Learning.
Role in this project:
userML Engineer
Contributions:1 review, 17 commits, 3 PRs in 3 years 2 months
Contributions summary:Moamen's contributions primarily focused on integrating and modifying deep learning models within the PyTorch project template. They added support for the ERFNet model, a semantic segmentation architecture, and addressed a warning in the summary writer. Furthermore, the user implemented weighted loss calculations for ERFNet, enhancing the training process. The user also made modifications to the DQN agent and the CondenseNet agent files, reflecting ongoing developments and testing.
classificationimage-segmentationpytorchreinforcement-learningpytorch-template
Contributions:25 pushes, 1 branch in 1 month
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial