Attila Csok
Software Engineer at Movidius
Timișoara, Timiș, Romania
Summary
🤩
Rockstar🎓
Top SchoolAttila Csok is a software engineer based in Timișoara with about two years of hands-on experience delivering backend C++ work for AI inference tooling. At Movidius he has focused on Intel NPU plugin development within the widely used OpenVINO open-source project, implementing device properties, PCI info retrieval, and optimization features such as turbo and QDQ handling while addressing driver and compiler compatibility. Trained in Systems Engineering at Universitatea Politehnica din Timișoara, he blends low-level systems thinking with practical deployment concerns. Early experience in web/print design and network/server administration gives him a pragmatic, cross-disciplinary perspective on engineering and operations. Notably, his contributions improve how hardware capabilities and compiler behavior are exposed to higher-level inference stacks, making device-aware optimizations more reliable in production.
2 years of coding experience
Systems Engineering, Systems Engineering at Universitatea „Politehnica” din Timișoara
Github Skills (17)
c-language10
plugin-development10
openvino10
device-driver10
cprogramming-language10
computer-vision9
compiler-options9
inference9
compile9
ai9
compiler9
performance-tuning8
performance-analysis8
performance-measurement8
performance-monitor8
Programming languages (1)
Github contributions (2)
openvinotoolkit/openvino
Apr 2024 - Mar 2025
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer
Back-end DeveloperContributions:62 reviews, 54 PRs, 67 comments in 11 months
Contributions summary:Attila primarily contributed to the Intel NPU plugin, focusing on adding and modifying properties related to device features and compiler behavior. Their work involved modifying C++ code, specifically in files related to device properties and compiler configuration, to enable functionalities like retrieving PCI information, implementing DEVICE_GOPS and DEVICE_TYPE properties, and adding turbo and QDQ optimization features. The contributions also included adjustments to handle compatibility issues with older driver versions and compiler configurations.
inference-enginepytorchmodel-optimizerdeep-learninggpu
csoka/openvino
Apr 2024 - Mar 2025
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Contributions:2 PRs, 155 pushes, 53 branches in 11 months
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.