Yury Gaydaychuk
Software Engineer at Intel Corporation
Munich, Bavaria, Germany
Summary
🤩
Rockstar🎓
Top SchoolYury Gaydaychuk is a software engineer based in Munich with six years of experience building high-performance back-end systems, currently working at Intel. He focuses on ML inference optimization, contributing to the widely used OpenVINO toolkit by improving CPU implementations for ROIAlign, PSROIPooling, and deformable convolutions with bfloat16 and multiple data-layout support. His work blends practical performance tuning, careful refactoring, and test-driven validation to make ML workloads faster and more robust in production. Comfortable with low-level details and mathematics, he brings a developer’s rigor to numerical and layout-sensitive problems. Before Intel he worked on embedded and connected services at HARMAN, giving him exposure to both consumer-facing and enterprise software stacks.
6 years of coding experience
1 year of employment as a software developer
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at State University of Nizhni Novgorod named after N.I. Lobachevsky (UNN)
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (10)
cpu10
c-language10
cprogramming-language10
performance-optimization10
openvino10
inference9
bfd9
deep-learning8
deeplearning-ai8
computer-vision8
Programming languages (1)
Github contributions (5)
openvinotoolkit/openvino
Dec 2020 - Sep 2022
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer
Back-end DeveloperContributions:280 reviews, 28 commits, 177 PRs in 1 year 9 months
Contributions summary:Yury's commits primarily focus on enhancing the CPU implementation for the OpenVINO toolkit, with a specific emphasis on the ROIAlign, PSROIPooling, and Deformable Convolution nodes. These enhancements include support for bfloat16 data types, and handling various data layouts like NHWC and BLOCKED formats. The contributions involved code refactoring, performance improvements, and the addition of CPU-specific tests to validate the correctness of the implemented features, with the goal of optimizing and deploying AI inference.
inference-enginepytorchmodel-optimizerdeep-learninggpu
yury-intel/openvino
Jun 2020 - Apr 2025
OpenVINO™ Toolkit - Deep Learning Deployment Toolkit repository
Contributions:8 reviews, 8 PRs, 939 pushes in 4 years 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.