Vladimir Zinoviev
AI Software Engineer at YADRO
Nizhny Novgorod, Nizhny Novgorod Oblast, Russia
Summary
🤩
Rockstar🎓
Top SchoolVladimir Zinoviev is an AI software engineer with 11 years of experience building and optimizing inference and computer vision systems, currently working at YADRO out of Nizhny Novgorod. He has a strong track record at Intel contributing to OpenVINO’s Inference Engine and to oneDNN performance kernels, including low-level SSE42 optimizations for 1x1 convolutions and LRN improvements. Vladimir combines systems-level performance engineering with practical interoperability work—enhancing OpenCV’s DirectX pipelines and NV12 support to streamline GPU↔CPU image workflows. He is comfortable across the stack, from C++ kernel tuning and memory-copy elimination to migrating samples to new APIs and improving benchmark tooling. An active open-source contributor, he focuses on production-ready speed and maintainability in widely used ML toolkits and demos. Colleagues would note his knack for spotting small inefficiencies that yield measurable inference and throughput gains.
11 years of coding experience
4 years of employment as a software developer
Нижегородский Государственный Университет им. Н.И. Лобачевского (ННГУ)
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (33)
opencl10
opencv10
performance-monitor10
c-language10
python10
image-processing10
inference10
modello10
openvino10
ml10
x8610
mle10
deep-learning10
performance-analysis10
sse10
Programming languages (5)
Github contributions (5)
openvinotoolkit/open_model_zoo
May 2019 - Nov 2022
Pre-trained Deep Learning models and demos (high quality and extremely fast)
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:1122 reviews, 488 commits, 672 PRs in 3 years 6 months
Contributions summary:Vladimir contributed to the `open_model_zoo` repository by merging and modifying various demo files, primarily related to the image retrieval and text spotting demos. The changes involve fixing minor issues, updating test cases and documentation, and syncing documentation to the demo text. The modifications indicate a focus on improving the functionality and maintainability of the demo applications, suggesting that the user is involved in the development and upkeep of example projects.
modelonnx-modelsdeep-learning-modelsmodel-zoopytorch-models
openvinotoolkit/openvino
Sep 2021 - Jan 2023
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Role in this project:ML Engineer
ML EngineerContributions:153 reviews, 31 commits, 97 PRs in 1 year 3 months
Contributions summary:Vladimir contributed to the OpenVINO™ toolkit by addressing various issues and enhancing existing functionalities. Their work involved fixing typos in documentation, adding a performance hint option in the benchmark application, limiting supported formats in a sample, and eliminating memory copies. Additionally, the user made substantial changes to the hello_reshape_ssd sample, aligning it with the OV2.0 API and also modified python sample code to migrate to OV 2.0 API. This indicates an involvement in model optimization, inference, and sample maintenance.
inference-enginepytorchmodel-optimizerdeep-learninggpu
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.