Grzegorz R

Python Developer at Transition Technologies PSC

Poland
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Grzegorz R is a Python developer with five years of engineering experience and a background in silicon firmware development from his time at Intel. He combines backend and performance engineering skills—demonstrated by contributions to the high-profile oneDNN library where he implemented optimized GPU kernels and improved f16 precision—with practical Python web and systems work across agencies and product shops. Currently working in Poland at Transition Technologies PSC and People Trust, he has a track record of shipping Django and backend services at companies like Merixstudio and 10Clouds. Comfortable bridging low-level performance tuning and higher-level application development, he brings a pragmatic, optimization-first mindset to production systems.
code5 years of coding experience
job4 years of employment as a software developer
bookInżynier (Inż.) Teleinformatyka, Inżynier (Inż.) Teleinformatyka at Wrocław University of Science and Technology
github-logo-circle

Github Skills (13)

opencl10
gpu-programming10
c-language10
cprogramming-language10
performance-optimization10
simd9
deep-learning8
neural-network8
deep-neural-networks8
x86-647
x867
avx6
arm5

Programming languages (1)

C++

Github contributions (1)

github-logo-circle
uxlfoundation/oneDNN

Jul 2020 - Oct 2021

oneAPI Deep Neural Network Library (oneDNN)
Role in this project:
userBack-end Developer & Performance Engineer
Contributions:7 reviews, 48 commits, 2 PRs in 1 year 2 months
Contributions summary:Grzegorz primarily focused on optimizing the performance of the oneDNN library, specifically targeting the GPU backend. Their contributions included implementing new kernel implementations for reorder operations, such as transpose and various blocking formats. They addressed performance bottlenecks by implementing specialized kernels and optimizing existing ones. They also worked on improving the precision of calculations, specifically for the f16 data type.
bfloat16sse41avx512openmpopencl
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.
Request Free Trial
Grzegorz R - Python Developer at Transition Technologies PSC