Roman Kazantsev
AI Frameworks Engineer, Technical Lead at Intel Corporation
Dubai, Dubai, Russia
Summary
🤩
Rockstar🎓
Top SchoolRoman Kazantsev is an AI frameworks engineer and technical lead with over a decade of hands-on experience in Python, C/C++, and x86 assembly, specializing in video compression, machine learning, and deep learning inference on Intel hardware. At Intel he leads development of the OpenVINO Model Optimizer, adding TensorFlow 2 support and enabling complex recommender and CV models for efficient deployment across Intel platforms. His background spans DRM and cryptographic protections, high-performance computing optimizations, and low-level video codec work—contributions that include codec feature enhancements in the widely used Intel Media SDK. A pragmatic team player and code reviewer, he blends research output (four publications and a patent) with production-grade engineering and has presented security and anti-cheat work at international conferences. Based in Dubai with roots in Russia, he pairs academic rigor (MS degrees from UNN and MSU) with measurable impact on open-source and proprietary media and AI tooling.
10 years of coding experience
9 years of employment as a software developer
Bachelor's degree, Information Technology, Bachelor's degree, Information Technology at State University of Nizhni Novgorod named after N.I. Lobachevsky (UNN)Lomonosov Moscow State University
English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (5)
video-processing10
c-language10
vaapi10
cprogramming-language10
color-conversion10
Programming languages (5)
Github contributions (5)
Intel-Media-SDK/MediaSDK
Jan 2018 - Apr 2018
The Intel® Media SDK
Role in this project:
Back-end Developer
Back-end DeveloperContributions:15 commits, 10 PRs, 31 pushes in 3 months
Contributions summary:Roman primarily contributed to the Intel Media SDK, focusing on video processing and color conversion functionalities. Their work involved adding support for new color formats like P010 and RGB565, and implementing features such as horizontal mirroring and low-power scaling modes within the VPP (Video Processing Pipeline). Furthermore, the user worked on enabling VP9 codec features, enhancing the decoding capabilities of the SDK.
intel-media-sdkintelsdkvideomfx
rkazants/openvino
May 2020 - Mar 2025
OpenVINO™ Toolkit - Deep Learning Deployment Toolkit repository
Contributions:1718 pushes, 705 branches in 4 years 10 months
pytorchcaffe2deep-learningdeploymentopenvino-toolkit
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.