Maksim Doronin
AI Software Engineering Manager at Intel Corporation
Dublin, Ireland
Summary
🤩
Rockstar🎓
Top SchoolMaksim Doronin is an AI software engineering manager with 10 years of experience leading development and delivery of VPU-focused inference software at Intel, currently based in Dublin. He has deep hands-on expertise across firmware, runtime, compiler passes and plugins for OpenVINO, having driven quality, performance and release readiness for MyriadX and next-generation VPU integrations. Maksim combines people leadership with active backend contributions—his open-source work on OpenVINO’s Inference Engine (notably VPU reshape/outshape, dynamic ops and s32->u8 conversion) reflects both low-level optimization skill and rigorous testing. Prior roles include full‑stack VPU engineering and Chromium-based mobile browser development at Yandex, giving him a rare blend of hardware-aware ML deployment and consumer software experience. Colleagues rely on him to translate complex accuracy and performance requirements into reproducible CI-backed releases, and he often bridges driver/firmware teams with higher-level product changes.
10 years of coding experience
5 years of employment as a software developer
Bachelor's degree, Computer and Information Sciences, General, Bachelor's degree, Computer and Information Sciences, General at State University of Nizhni Novgorod named after N.I. Lobachevsky (UNN)
Github Skills (11)
c-language10
inference10
cprogramming-language10
openvino10
optimization9
optimisation9
optimizer9
deep-learning9
computer-vision8
testing8
ai8
Programming languages (6)
Github contributions (5)
openvinotoolkit/openvino
Jun 2020 - Dec 2022
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer
Back-end DeveloperContributions:398 reviews, 35 commits, 247 PRs in 2 years 6 months
Contributions summary:Maksim primarily contributed to the Inference Engine (IE) VPU (Vision Processing Unit) component, specifically focusing on the "OutShapeOfReshape" operation. Their commits included implementing per-layer tests, updating firmware, and refactoring code to eliminate duplication. The contributions also involved enabling and testing s32->u8 conversion within the IE VPU framework and making dynamic broadcast tests. Furthermore, the user worked on fixing dynamic concat and DSR-related issues.
inference-enginepytorchmodel-optimizerdeep-learninggpu
openvinotoolkit/npu_compiler
Apr 2022 - Mar 2025
OpenVINO NPU Plugin
Contributions:8 releases, 26 reviews, 39 PRs in 3 years
compileropenvinovpu
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.