Maxim Vafin
AI Frameworks Engineer at Intel Corporation
Germany
Summary
🤩
Rockstar🎓
Top SchoolMaxim Vafin is an AI Frameworks Engineer at Intel with nine years of experience building and productionizing deep learning tooling. He contributes to the high-profile open-source OpenVINO toolkit, adding operations like ReduceL2 decomposition and LogSoftmax-5, fixing PyTorch frontend tensor issues, and improving shape inference to better support advanced models. Trained as a systems engineer with a master's in Flight Dynamics from Bauman Moscow State Technical University, he brings rigorous analytical thinking to model optimization and inference pipelines. Based in Germany, Maxim blends low-level framework work with practical ML engineering to make deployments more robust and performant. Colleagues describe him as a pragmatic problem-solver who surfaces subtle shape and type bugs before they reach production.
9 years of coding experience
Master's degree, Flight Dynamics and Aircraft Movement Control, Master's degree, Flight Dynamics and Aircraft Movement Control at Московский Государственный Технический Университет им. Н.Э. Баумана (МГТУ) / Bauman Moscow State Technical University
Russian, English
Stackoverflow
33reputation
2kreached
0answers
6questions
Github Skills (17)
pytorch10
operation10
tensorrt10
machine-learning10
openvino10
deep-learning10
tensorflow10
tensor10
google-play6
google-play-services6
scene2d6
android6
google-play-games6
libgdx6
java6
Programming languages (3)
Github contributions (5)
openvinotoolkit/openvino
May 2020 - Jan 2023
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
Role in this project:
ML Engineer
ML EngineerContributions:2297 reviews, 130 commits, 795 PRs in 2 years 8 months
Contributions summary:Maxim implemented and tested new operations for the OpenVINO toolkit, focusing on supporting advanced deep learning models. Their contributions include the addition of ReduceL2 decomposition and the implementation of the LogSoftmax-5 operation, along with corresponding tests. Furthermore, the user fixed issues related to tensor types in the PyTorch frontend and improved handling of shape inferences for specific operations.
aiinferenceopenvinodeep-learningcomputer-vision
mvafin/openvino
May 2020 - Jul 2026
OpenVINO™ Toolkit - Deep Learning Deployment Toolkit repository
Contributions:10 reviews, 26 PRs, 2354 pushes in 6 years 2 months
deep-learningopenvino
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.