Ondřej Jamriška

Founder at EbSynth

Prague, Czechia
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
Ondřej Jamriška is a founder and seasoned software engineer with 11 years of experience blending research-grade computer vision and high-performance systems engineering. Based in Prague, he moved from a decade as a research scientist at Czech Technical University to founding EbSynth, applying deep technical skills to practical imaging tools. His open-source work shows strong low-level optimization expertise—rewriting CUDA kernels, adding CPU backends and polishing passes for fast example-based style transfer—and a rare full-stack shader and cross-language fluency demonstrated in a multi-language color-mixing library. Ondřej combines academic rigor with product-minded execution, able to turn complex algorithms into efficient, cross-platform implementations.
code11 years of coding experience
job9 years of employment as a software developer
bookM.S., Computer Science, M.S., Computer Science at Czech Technical University in Prague
languagesEnglish, Czech
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
0answers
0questions
github-logo-circle

Github Skills (20)

javascript10
c-language10
shader10
python10
rgba10
gpu-programming10
glsl10
colors10
style-transfer10
java10
metal10
javas10
parallel-computing10
dotnet-core10
cuda10

Programming languages (3)

C#C++C

Github contributions (5)

github-logo-circle
jamriska/ebsynth

Apr 2018 - May 2019

Fast Example-based Image Synthesis and Style Transfer
Role in this project:
userBack-end Developer
Contributions:15 commits, 13 pushes in 1 year
Contributions summary:Ondřej primarily contributed to the core functionality of the `ebsynth` project. Their work involved significant changes to the CUDA code, optimizing memory allocation and improving the random search kernel. They also added a CPU backend and introduced an option for a 3x3 polishing pass, demonstrating a focus on performance and expanding the project's capabilities. These changes reveal an emphasis on computational efficiency and supporting different hardware platforms.
example-basedsynthesisstyle-transferimage-synthesisimage-analogy
scrtwpns/mixbox

Dec 2021 - Dec 2022

Mixbox is a library for natural color mixing based on real pigments.
Role in this project:
userFull-stack Developer
Contributions:22 commits in 1 year
Contributions summary:Ondřej's primary contribution involved adding and refining Mixbox, a library for color mixing. They introduced code for C++, shader languages (GLSL, HLSL, and Metal), JavaScript, Python, Java, C#, and Rust, demonstrating broad cross-platform development capabilities. The user implemented shader code to render colors effectively. They added functionality across multiple languages for implementing the project.
mixingrgbpaintsnaturalcolor-mixing
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