Andrey Sokolov
Software Engineer at YADRO
Nizhny Novgorod, Nizhny Novgorod Oblast, Russia
Summary
🤩
Rockstar🎓
Top SchoolAndrey Sokolov is a software engineer with 8 years of experience specializing in back-end development and machine learning inference for computer vision. Based in Nizhny Novgorod, he has contributed significant optimizations to the high-profile openvino open-source toolkit, improving VPU support, layer implementations (ROIAlign, GatherElements, NMS), firmware, and batch processing to boost performance and reduce memory use. He transitioned from an internship at Intel to a full engineering role at YADRO, pairing industry experience with a master’s in applied mathematics and computer science from UNN. Andrey’s work reflects a practical focus on production-ready ML inference and low-level performance tuning rather than just research prototypes. He tends to solve efficiency bottlenecks by refactoring and targeted firmware updates, demonstrating attention to both algorithmic correctness and hardware constraints. Colleagues can expect a developer who bridges theoretical CS education with hands-on optimization of real-world AI deployment stacks.
8 years of coding experience
Master's degree Applied mathematics and computer science, Master's degree Applied mathematics and computer science at State University of Nizhni Novgorod named after N.I. Lobachevsky (UNN)
Github Skills (10)
computer-vision10
deeplearning-ai10
c-language10
inference10
deep-learning10
cprogramming-language10
ai10
openvino10
optimization9
python4
Programming languages (1)
Github contributions (4)
openvinotoolkit/openvino
Jun 2020 - Feb 2021
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:113 reviews, 19 commits, 23 PRs in 8 months
Contributions summary:Andrey primarily focused on optimizing the OpenVINO toolkit, specifically targeting the VPU (Vision Processing Unit) and related layers. Their contributions include updating firmware, optimizing and refactoring code for layers such as ROIAlign, Ceiling, and GatherElements, and adjusting batch processing to improve performance and memory consumption. Furthermore, they made improvements to the NMS (Non-Maximum Suppression) layer and added support for new operations, indicating a focus on enhancing the toolkit's capabilities for computer vision and deep learning inference.
inference-enginepytorchmodel-optimizerdeep-learninggpu
andrejsokolov/openvino
May 2020 - Jan 2022
OpenVINO™ Toolkit - Deep Learning Deployment Toolkit repository
Contributions:141 pushes, 28 branches in 1 year 7 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.