Marcin Kacprzak
AI Software Engineer at Intel Corporation
Gdańsk, Pomeranian Voivodeship, Poland
Summary
🤩
Rockstar🎓
Top SchoolMarcin Kacprzak is an AI Software Engineer based in Gdańsk with over three years focused on ML inference and a decade-plus background in embedded and backend systems. At Intel he sharpens OpenVINO’s GNA plugin—optimizing int8 convolution scaling, fixing Concat-layer issues, and improving ExecutionMode support—to get AI models running accurately on specialized hardware. His earlier roles at UTC Fire & Security show deep systems engineering chops: building elastic HW testing platforms, secure device key exchange, high-throughput alarm receivers, and auto-discovery protocols across C/C++, Java, Python and TypeScript stacks. Comfortable across low-level device integration and higher-level web and cloud interfaces, he blends pragmatic debugging with protocol and performance design. Multilingual and creative, he combines long-term embedded experience with applied ML engineering to bridge model accuracy and real-world deployment constraints.
3 years of coding experience
19 years of employment as a software developer
Master of Sience, Multimedia Techniques, Master of Sience, Multimedia Techniques at Technical University of Gdansk
Polish, English, German
Github Skills (8)
c-language10
deep-learning10
inference10
cprogramming-language10
ai10
openvino10
neural-network9
convolutional-neural-networks9
Programming languages (1)
Github contributions (4)
openvinotoolkit/openvino
Nov 2022 - 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:126 reviews, 1 commit, 10 PRs in 1 day
Contributions summary:Marcin primarily contributed to the Intel GNA plugin within the OpenVINO toolkit, focusing on optimizing and debugging the inference process on Intel's GNA hardware. Their work involved fixing calculation issues for int8 convolution weights, specifically addressing scale factor calculations and input generation within the GNA framework. Furthermore, the user was involved in resolving issues related to Concat layers and implementing support for ExecutionMode, demonstrating a focus on improving the plugin's accuracy and performance.
inference-enginepytorchmodel-optimizerdeep-learninggpu
marcinkacprzak/openvino
Sep 2022 - Sep 2023
OpenVINO™ Toolkit repository
Contributions:122 pushes, 15 branches in 1 year
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.