Eugene Smirnov
Senior Software Engineer at Intel Corporation
Munich, Bavaria, Germany
Summary
🤩
Rockstar🎓
Top SchoolEugene Smirnov is a Senior Software Engineer based in Munich with eight years of professional experience building and optimizing ML inference tooling. At Intel he focuses on low-level performance and correctness, contributing notable improvements to the OpenVINO toolkit—especially the GNA plugin where he implemented and tested FakeQuantize functionality and helped bridge fp32/fp16 conversions. His applied mathematics master's grounds his analytical approach to numerical precision and plugin integration challenges. Eugene combines production-focused engineering with open-source collaboration, addressing legacy test failures and architectural fuses that improve deployable AI inference. He excels at making inference pipelines both faster and more robust, with a knack for practical fixes that reduce surprises in complex CI and deployment flows.
8 years of coding experience
Master's degree, Applied Mathematics, Master's degree, Applied Mathematics at Нижегородский Государственный Университет им. Н.И. Лобачевского (ННГУ)
Github Skills (10)
deep-learning10
ai10
openvino10
optimization9
cprogramming-language9
c-language9
inference9
computer-vision9
unit-testing8
mlops5
Programming languages (2)
Github contributions (5)
openvinotoolkit/openvino
Jul 2020 - Sep 2020
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
Role in this project:
ML Engineer
ML EngineerContributions:123 reviews, 5 commits, 32 PRs in 2 months
Contributions summary:Eugene's contributions primarily focus on optimizing the OpenVINO toolkit, specifically within the GNA plugin. They implemented and tested fake quantize functionality for the GNA plugin, including fp32 implementation and seed randomization. The user also worked on fixing legacy unit test failures related to the GNA plugin and adopted fuse multiple identities for the FakeQuantize layer. Additional contributions include supporting conversion between fp32 and fp16 types for ngraph_helpers, and modifying code related to NPUW plugin.
inference-enginepytorchmodel-optimizerdeep-learninggpu
esmirno/openvino
May 2020 - Mar 2025
OpenVINO™ Toolkit - Deep Learning Deployment Toolkit repository
Contributions:2 PRs, 109 pushes, 19 branches in 4 years 10 months
pytorchdeep-learningdeploymentopenvino-toolkitobject-detection
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.