Nikita Malinin
Deep Learning Engineer at YADRO
Russia
Summary
🤩
Rockstar🎓
Top SchoolNikita Malinin is a Deep Learning Engineer with 8 years of experience specializing in making neural networks faster and more accurate at inference. He has driven backend and ML engineering work on high-profile open-source projects such as OpenVINO and NNCF, contributing C++ transformations, test updates, and API improvements that support production inference and post-training optimization. His industry experience spans Intel research roles focused on model compression and PTQ, a computer vision post at Medical Visual Systems, and current work at YADRO, blending research-grade rigor with practical deployment. Trained in mechatronics and robotics, he brings a systems-level perspective to model optimization, often tackling device-specific challenges like GNA integration that are easy to overlook.
8 years of coding experience
11 years of employment as a software developer
Master's degree Mechatronics robotics and automation, Master's degree Mechatronics robotics and automation at Nizhniy Novgorod State Technical University named after R.Y. Alekseev (NSTU)
Github Skills (17)
c-language10
python10
back-end-development10
inference10
onnx10
openvino10
deeplearning-ai10
deep-learning10
ai10
quantization10
backend10
cprogramming-language10
apidoc9
machine-learning9
api9
Programming languages (4)
Github contributions (5)
openvinotoolkit/nncf
Mar 2022 - Jan 2023
Neural Network Compression Framework for enhanced OpenVINO™ inference
Role in this project:
Back-end Developer
Back-end DeveloperContributions:11 releases, 1353 reviews, 23 commits in 9 months
Contributions summary:Nikita's contributions centered on the development and improvement of the `nncf` library. The commits focused on refactoring code, adding comments, and addressing Pylint issues to improve code quality and maintainability. The user also worked on removing backend-specific methods and updating samplers, indicating a focus on optimizing the core functionality of the library. Further contributions involved updates to the PTQ API and engine, suggesting the user's involvement in improving the usability and performance of the neural network compression framework.
bertsemantic-segmentationmixed-precision-trainingtensorflowclassification
openvinotoolkit/openvino
Apr 2021 - Dec 2022
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:110 reviews, 39 commits, 61 PRs in 1 year 7 months
Contributions summary:Nikita primarily contributed to the OpenVINO toolkit by adding transformations and updating tests, specifically focusing on the GNA device. Their work involved modifying C++ code related to inference engine transformations and updating Python-based test scripts within the POT (Post-Training Optimization Toolkit) directory. The contributions involved updating the POT tests with new data, removing models from the tests, and updating the benchmark.py IE Python API usage.
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.