Egor Duplenskii
AI Frameworks Engineer at Intel Corporation
Munich, Bavaria, Germany
Summary
🤩
Rockstar🎓
Top SchoolEgor Duplenskii is an AI Frameworks Engineer based in Munich with 9 years of experience building and optimizing deep learning infrastructure, currently driving framework and inference performance at Intel. He specializes in back-end performance engineering—particularly CPU inference optimizations—and has contributed notable fixes and benchmark improvements to the widely used open-source OpenVINO toolkit, including bfloat16 precision support and sanitization-build fixes. Prior to Intel he spent seven years as a software engineer at MERA and holds a Master's in Computer Science, giving him a solid foundation in systems and software engineering. Known for pragmatic, low-level improvements that yield measurable speed and reliability gains, he blends research-aware thinking with production-grade implementation.
9 years of coding experience
7 years of employment as a software developer
Master's degree, Computer Science, Master's degree, Computer Science at Nizhniy Novgorod State Technical University named after R.Y. Alekseev (NSTU)
Github Skills (8)
cpu-architecture10
c-language10
cprogramming-language10
performance-optimization10
benchmark9
benchmarking9
cmake8
bfd8
Programming languages (13)
Github contributions (5)
openvinotoolkit/openvino
Mar 2021 - Jan 2023
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:1146 reviews, 64 commits, 253 PRs in 1 year 10 months
Contributions summary:Egor's contributions primarily focused on optimizing the OpenVINO toolkit's CPU performance. Their commits involved disabling and re-implementing optimizations for CPU-related components. The user also implemented fixes for sanitization builds, which improved the resolving of library symbols. Additionally, they contributed to improvements in benchmark applications to enable the precision of bfloat16.
inference-enginepytorchmodel-optimizerdeep-learninggpu
EgorDuplensky/openvino
Feb 2021 - Apr 2025
Fastest inference framework
Contributions:888 pushes, 227 branches in 4 years 1 month
pytorchdeep-learninggpuopenvino-toolkitcomputer-vision
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.