Svetlana Dolinina
Sr. Software Engineer at Huawei
Gezer Regional Council, Center District, Russia
Summary
🤩
Rockstar🎓
Top SchoolSvetlana Dolinina is a Senior Software Engineer with six years of professional experience, currently driving backend and tooling work at Huawei after a long tenure at Intel. She specializes in model optimization and tooling for AI inference—contributing to the high-profile OpenVINO project by hardening the model optimizer, adding API-refining refactors, and shipping tests to prevent IR generation issues. Her background spans cross-platform engineering (including porting Android core to iOS) and building Python-based converters to migrate neural networks from frameworks like Caffe and Kaldi into internal formats. Trained as an Applied Mathematics master, she brings a rigorous analytical approach to debugging complex ML pipelines and API design while balancing practical engineering with test-driven quality improvements.
5 years of coding experience
15 years of employment as a software developer
магистр, Applied Mathematics, магистр, Applied Mathematics at Нижегородский Государственный Университет им. Н.И. Лобачевского (ННГУ)
Github Skills (11)
graph10
python10
openvino10
model-optimization10
test-automation10
cprogramming-language9
machine-learning9
c-language9
inference9
deep-learning8
computer-vision7
Programming languages (1)
Github contributions (3)
openvinotoolkit/openvino
Sep 2020 - Apr 2022
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer & Test Automation Engineer
Back-end Developer & Test Automation EngineerContributions:382 reviews, 42 commits, 49 PRs in 1 year 6 months
Contributions summary:Svetlana primarily focused on enhancing the OpenVINO toolkit's model optimizer, specifically implementing checks for input shape validation to prevent IR generation errors. They also contributed to adding sinks to the ngraph::Function and refactored the code to move QueryState from ExecutableNetwork to InferRequest to improve API design. Further, the user was instrumental in fixing bugs and making improvements to the model optimizer by including tests to ensure code quality and correct functionality.
inference-enginepytorchmodel-optimizerdeep-learninggpu
sadolini/openvino
May 2020 - Apr 2022
OpenVINO™ Toolkit - Deep Learning Deployment Toolkit repository
Contributions:3 PRs, 410 pushes, 75 branches in 1 year 10 months
pytorchdeep-learningdeploymentopenvino-toolkitinference
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.