Sergey Korobkov
Software Development Engineer at Intel Corporation
Dubai, Dubai, United Arab Emirates
Summary
🤩
RockstarSergey Korobkov is a Software Development Engineer based in Dubai with eight years of experience spanning network security and backend ML engineering. He transitioned from hands-on network and security roles—holding CCNP, CCSP and CheckPoint CSE certifications—into software development at EPAM and now Intel, where he contributes to AI inference tooling. At Intel he has worked on OpenVINO internals, improving nGraph RTTI, dynamic shape handling and efficient FP32→FP16 conversions, blending low-level systems thinking with ML deployment needs. His background in configuring and automating complex security infrastructures gives him a practical reliability mindset when building production-grade ML components. Colleagues describe him as a pragmatic engineer who bridges networking, security and ML inference engineering. He brings an unusual combination of deep networking security credentials and proven contributions to a major open-source AI toolkit.
8 years of coding experience
11 years of employment as a software developer
Github Skills (22)
c-language10
openvino10
type-system10
model-optimization10
cprogramming-language10
performance-monitor9
performance-analytics9
performance-measurement9
performance-monitoring9
deep-learning9
performance-analysis9
performance-tuning9
computer-vision8
optimization8
architectures8
Programming languages (5)
Github contributions (5)
openvinotoolkit/openvino
Aug 2020 - Nov 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:813 reviews, 8 commits, 76 PRs in 2 years 3 months
Contributions summary:Sergey primarily worked on extending the nGraph RTTI system within the OpenVINO toolkit, focusing on type-related features and optimizations. Their commits involve refactoring and migrating operations to the new RTTI, including defining and applying macros for type identification. In addition, the user implemented and tested a TypeRelaxed template class and contributed to dynamic shape handling within the plugin, specifically in regards to dynamic shapes documentation. They also implemented an efficient conversion from FP32 to FP16.
inference-enginepytorchmodel-optimizerdeep-learninggpu
slyalin/openvino
Jun 2020 - Mar 2025
OpenVINO™ Toolkit - Deep Learning Deployment Toolkit repository
Contributions:122 reviews, 111 PRs, 481 pushes 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.