Evgeny Kotov
Senior Software Engineer at Intel Corporation
Germany
Summary
🤩
Rockstar🎓
Top SchoolEvgeny Kotov is a Senior Software Engineer based in Germany with over 5 years in his current senior roles and two decades of systems-level C/C++ experience across Linux environments. He specializes in OpenVINO GNA backend development at Intel, contributing optimizations and unit tests that improve neural network inference for specialized hardware. His background includes high-load backend and search indexing systems at Mail.Ru and long-standing work on mandatory access control and OS component integrations at a Russian research institute, giving him deep expertise in security-conscious system design. Comfortable across C, C++, Python and build systems, he bridges low-level performance engineering with practical ML deployment concerns. Notably, his open-source contributions to the widely used OpenVINO toolkit focus on transformation passes (transpose/reshape/MatMul optimizations) that enable efficient model mapping to GNA accelerators. He holds a Master’s in Applied Mathematics and System Software Development from MEPhI, combining rigorous academic foundations with production-grade engineering.
4 years of coding experience
19 years of employment as a software developer
Master's degree, Applied Mathematics, System Software Development, Master's degree, Applied Mathematics, System Software Development at National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)
Github Skills (10)
computer-vision10
deeplearning-ai10
deep-q-learning10
deep-learning10
ai10
openvino10
optimization10
unit-testing9
c-language8
cprogramming-language8
Programming languages (1)
Github contributions (5)
openvinotoolkit/openvino
Jun 2021 - Jan 2023
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Role in this project:
ML Engineer
ML EngineerContributions:242 reviews, 24 commits, 131 PRs in 1 year 6 months
Contributions summary:Evgeny primarily contributes to the OpenVINO™ toolkit, which is designed for optimizing and deploying AI inference. Their work involves implementing unit tests and transformations focused on optimizing neural network models for GNA (Gaussian Neural Accelerator) hardware. The contributions span multiple transformations, including insertion of transpose operations before MatMul layers, extra reshape removals, and insertion of transpose operations after convolution or pooling layers. They also work on swapping MatMul input and converting MatMul to point-wise convolution for optimized model deployment.
inference-enginepytorchmodel-optimizerdeep-learninggpu
evkotov/openvino
Jun 2021 - Mar 2025
OpenVINO™ Toolkit repository
Contributions:837 pushes, 239 branches in 3 years 9 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.