Lukasz Wawrzyniak
Deep Learning Engineer at NVIDIA
Milton, Ontario, Canada
Summary
🤩
Rockstar🎓
Top SchoolLukasz Wawrzyniak is a Deep Learning Engineer with eight years of experience building GPU-accelerated systems at NVIDIA, based in Milton, Ontario. He combines academic depth as a long-time PhD candidate in Computer Science at the University of Guelph with practical expertise shipping CUDA-integrated features and build-system fixes for high-performance Python frameworks. At NVIDIA he has focused on bridging C++/CUDA and Python, contributing precise numeric routines and improving module loading and cross-platform robustness in notable projects like NVIDIA/warp. Earlier roles in academia and program coordination honed his research rigor and cross-functional communication, enabling him to translate complex computational needs into reliable engineering deliverables. Colleagues describe him as detail-oriented with a knack for low-level performance work that quietly improves developer ergonomics and numerical correctness.
8 years of coding experience
5 years of employment as a software developer
PhD Candidate, Computer Science, PhD Candidate, Computer Science at University of Guelph
Github Skills (11)
cuda10
warp10
gpu-programming10
python10
cprogramming-language9
math9
build-system9
c-language9
mathematics9
linux8
performance-optimization8
Programming languages (1)
Github contributions (5)
NVIDIA/warp
Feb 2022 - Jan 2023
A Python framework for high performance GPU simulation and graphics
Role in this project:
Back-end Developer
Back-end DeveloperContributions:4 reviews, 104 commits, 40 comments in 11 months
Contributions summary:Lukasz's primary contribution involved exposing rounding functions within the Warp framework, a Python framework for high-performance GPU simulation and graphics. They implemented and documented new math functions like round, rint, trunc, floor, and ceil in both the Python context and the underlying C++ code, including the CUDA implementation. Additionally, the user fixed various build warnings and bugs related to module reloading on Linux, as well as improving CUDA module loading, which demonstrates strong knowledge of build systems and CUDA integration within the project. The user has also enhanced the codebase by adding print overloads for all numeric types.
cudapythongpucomputer-graphicssimulation
nvlukasz/warp
Feb 2024 - Feb 2025
A Python framework for high performance GPU simulation and graphics
Contributions:12 PRs, 50 pushes, 5 branches in 1 year
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.