Nikita Kudriavtsev
AI Frameworks Engineer at Intel Corporation
Dublin, Ireland
Summary
🤩
Rockstar🎓
Top SchoolNikita Kudriavtsev is an AI Frameworks Engineer based in Dublin with six years of experience building and optimizing inference software for NPU and VPU devices. At Intel he develops neural network compilers and previously contributed to the Myriad plugin in OpenVINO, focusing on data transfer optimization, firmware/device boot integration, and performance tuning for constrained hardware. His background spans C/C++ systems work, computer vision pipelines, and user-facing tools across embedded, desktop, and mobile platforms, grounded in a master’s in Mathematics and Computer Science. An active contributor to the widely used open-source OpenVINO toolkit, he has hands-on expertise reducing DMA contention and improving test reliability on Myriad devices—details that highlight a pragmatic focus on resource efficiency often invisible to end users. Practical, detail-oriented, and comfortable bridging low-level performance engineering with higher-level framework development, he thrives on making ML inference both faster and more reliable in production contexts.
5 years of coding experience
6 years of employment as a software developer
Master's degree, Mathematics and Computer Science, Master's degree, Mathematics and Computer Science at State University of Nizhni Novgorod named after N.I. Lobachevsky (UNN)
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (11)
c-language10
cprogramming-language10
performance-optimization10
openvino10
functional-testing10
jtest10
ai9
firmware9
computer-vision8
deeplearning-ai7
deep-learning7
Programming languages (2)
Github contributions (5)
openvinotoolkit/openvino
May 2020 - Feb 2021
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:87 reviews, 27 commits, 41 PRs in 8 months
Contributions summary:Nikita primarily contributed to the optimization and testing of the OpenVINO toolkit, specifically focusing on the Myriad platform. Their work involved correcting destruction orders in functional tests, replacing "printf" methods with "mvLog" for improved logging, and integrating new features related to device boot processes and firmware updates. Additionally, the user implemented changes to limit CMX-DMA requests, demonstrating a focus on performance tuning and resource management for the VPU platform.
inference-enginepytorchmodel-optimizerdeep-learninggpu
nikita-kud/openvino
May 2020 - Apr 2025
OpenVINO™ Toolkit - Deep Learning Deployment Toolkit repository
Contributions:217 pushes, 51 branches, 1 comment in 4 years 11 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.