Cliff Burdick
Principal Developer Technology Engineer at NVIDIA
Vista, California, United States
Summary
🤩
Rockstar🎓
Top SchoolCliff Burdick is a Principal Developer Technology Engineer at NVIDIA with 8 years of focused experience in high-performance GPU and CUDA/C++ optimizations and a total software career spanning two decades. He specializes in tuning numerical and signal-processing workloads for GPUs, bridging deep systems knowledge from roles at ViaSat and Lockheed Martin to drive production-ready performance improvements. At NVIDIA he contributes to projects like MatX, fixing subtle libcudacxx integration issues and hardening headers and build scripts to ensure reliable library interoperability. Cliff combines algorithmic insight—having built GPU and CPU signal-processing pipelines and capacity-optimization tools—with hands-on expertise in low-level C++ and build systems, making him effective at turning complex dependencies into robust, deployable software. Based in Vista, California, he holds a Computer Engineering background from Cal Poly SLO and is known for tackling tricky cross-library compatibility challenges that often go unnoticed until they break builds.
8 years of coding experience
18 years of employment as a software developer
California Polytechnic State University, San Luis Obispo
Github Skills (8)
cuda10
c-language10
gpgpu10
cprogramming-language10
gpu10
accelerated-computing10
hpc9
cmake9
Programming languages (11)
Github contributions (5)
NVIDIA/MatX
Oct 2021 - Jan 2023
An efficient C++17 GPU numerical computing library with Python-like syntax
Role in this project:
Back-end Developer
Back-end DeveloperContributions:14 releases, 653 reviews, 240 commits in 1 year 2 months
Contributions summary:Cliff primarily focused on working around bugs and deficiencies in the `libcudacxx` library when used with the `matx` library. Their commits involve adjustments to the `FindLibcudacxx.cmake` file, modifications to several header files (`matx_random.h`, `matx.h`, `matx_half_complex.h`, `matx_tensor.h`), and fixes within the `examples` directory. These changes appear to be aimed at ensuring correct operation of the `matx` library, by directly addressing issues with underlying dependencies.
cudagpu-programmingnumerical-computingpythoncpp
Viasat/nhd
Nov 2019 - Dec 2020
A Topology-Aware Custom Scheduler For Kubernetes
Contributions:1 review, 85 commits, 5 PRs in 1 year
schedulerkubernetestopology
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.