Andrey Sapozhnikov
Data Scientist
Russia
Summary
🤩
Rockstar🎓
Top SchoolAndrey Sapozhnikov is a data scientist with four years of experience building and optimizing ML systems, currently working on speech recognition research and production at SberDevices. He has practical deep learning engineering experience from Intel, focusing on quantization and optimization algorithms, and has contributed backend performance and functional-test improvements to the high-profile OpenVINO open-source toolkit—particularly the GNA plugin for hardware-accelerated inference. His background spans applied ML roles, from wage-prediction and NLP projects to prototyping hyper-casual games in Unity, reflecting a blend of research rigor and production-minded engineering. Comfortable across Python, model optimization, and low-level performance work, he brings a track record of closing gaps between experimental models and reliable deployment.
4 years of coding experience
1 year of employment as a software developer
Bachelor of Technology - BTech, Computer Programming, Bachelor of Technology - BTech, Computer Programming at Higher School of Economics
Github Skills (10)
c-language10
cprogramming-language10
performance-optimization10
openvino10
testing9
inference8
ai8
computer-vision7
deeplearning-ai7
deep-learning7
Programming languages (1)
Github contributions (3)
openvinotoolkit/openvino
Jul 2021 - Dec 2021
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:5 reviews, 11 commits, 12 PRs in 5 months
Contributions summary:Andrey primarily contributed to the GNA (Gaussian and Neural Accelerator) plugin, specifically focusing on functional test improvements, bug fixes, and performance optimizations. Their work involved modifying configuration files for test skipping, fixing test failures, and resolving issues related to GNA library transitions and 2D convolution decomposition. Furthermore, the user enhanced the plugin's functionality by enabling tests and refactoring existing code, indicating a strong understanding of the OpenVINO toolkit and its underlying hardware acceleration.
inference-enginepytorchmodel-optimizerdeep-learninggpu
andreysapozhn/openvino
Jun 2021 - Dec 2021
OpenVINO™ Toolkit repository
Contributions:69 pushes, 11 branches in 5 months
pytorchdeep-learninggpuopenvino-toolkitcomputer-vision
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.