Krzysztof Biniaś
Software Engineer At Intel at Intel Corporation
Gdańsk, Pomeranian Voivodeship, Poland
Summary
🤩
Rockstar🎓
Top SchoolKrzysztof Biniaś is a software engineer with a decade of professional experience, currently building systems at Intel from his base in Gdańsk. He programs primarily in C/C++ and Python and brings prior senior engineering and team leadership experience from a decade at BMTcom where he also handled architecture and project management. Krzysztof has contributed to the high-profile PaddlePaddle deep learning framework, optimizing MKL-DNN backend primitives for activations and batch normalization to boost performance in distributed ML workloads. His background blends rigorous engineering (MSc in Informatics) with practical cross-language development (C#, Java, MDL), making him comfortable across system, backend and ML engineering domains. Notably, he couples low-level performance tuning with an eye for architectural quality and reusable memory/data handling patterns.
10 years of coding experience
11 years of employment as a software developer
Master of Science, Engineer, Geodesy and Cartography, Master of Science, Engineer, Geodesy and Cartography at AGH University of Science and Technology in CracowMaster of Science, Engineer, Informatics, Master of Science, Engineer, Informatics at Gdansk University of Technology
English, Polish
Github Skills (9)
paddlepaddle10
machine-learning10
c-language10
deep-learning10
cprogramming-language10
python10
efficientnet10
neural-network9
distributed-training9
Programming languages (2)
Github contributions (5)
PaddlePaddle/Paddle
Mar 2018 - Aug 2019
PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:39 commits, 34 PRs, 1 branch in 1 year 4 months
Contributions summary:Krzysztof contributed to the MKL-DNN backend integration within the PaddlePaddle framework, focusing on optimizing activation functions and batch normalization. Their work involved implementing forward and backward passes, including the creation of memory primitives and reorder primitives for efficient data handling. The user also improved the codebase by reallocating memory for forward passes and caching input data for backward operations. This resulted in performance improvements related to the MKL-DNN backend and optimization within the PaddlePaddle's machine learning framework.
pytorchpythonparalleldeep-learningpaddlepaddle
kbinias/vs-code
Jan 2019 - Mar 2020
Visual Studio Code stuff
Contributions:9 commits, 8 pushes, 1 branch in 1 year 1 month
visual-studio-codevscodevscode-extensionvscode-pluginvisual-studio
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.