Seunghwa Kang
Senior System Software Engineer at NVIDIA
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolSeunghwa Kang is a Senior System Software Engineer based in Seattle with seven years at NVIDIA and a strong research foundation from a PhD at Georgia Tech and earlier work at Pacific Northwest National Laboratory. He specializes in high-performance, CUDA-accelerated systems and GPU libraries, contributing substantial back-end work to prominent open-source RAPIDS projects like cuGraph, raft, cuSignal, and cuDF. His contributions span core functionality, error-handling robustness, Cython/C++ integration, and large-scale refactors—demonstrating both low-level systems expertise and a focus on maintainability. Comfortable resolving complex merge conflicts and improving developer tooling, he brings a researcher's rigor to production-grade software. An understated strength is his ability to bridge academic research and industrial-scale engineering, translating advanced algorithms into reliable, debuggable libraries.
7 years of coding experience
8 years of employment as a software developer
BS, Electrical Engineering, BS, Electrical Engineering at Seoul National UniversityPhD, Electrical and Computer Engineering, PhD, Electrical and Computer Engineering at Georgia Institute of Technology
Github Skills (23)
graph-algorithms10
c-language10
python10
signal-processing10
gpu-programming10
cupy10
cython10
ccl10
cuda10
error-handling10
cprogramming-language10
graph-database9
refactor9
building-blocks9
refactoring9
Programming languages (6)
Github contributions (5)
rapidsai/cugraph
Feb 2019 - Jan 2023
cuGraph - RAPIDS Graph Analytics Library
Role in this project:
Back-end Developer
Back-end DeveloperContributions:1259 reviews, 589 commits, 272 PRs in 3 years 11 months
Contributions summary:Seunghwa's commits primarily focused on adding and initializing Python files, and importing various modules from the cugraph library to implement core functionalities. The code changes involved importing classes from `cugraph.community`, `cugraph.components`, `cugraph.link_analysis`, `cugraph.link_prediction`, `cugraph.structure`, and `cugraph.traversal` and added the necessary imports to submodules. Additionally, the commits include the addition of pxd files which are related to cython compiling.
cudagraph-analysisanalyticsgraph-analyticsgraphml
rapidsai/raft
Jun 2020 - Jul 2022
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
Role in this project:Back-end Developer
Back-end DeveloperContributions:33 reviews, 75 commits, 19 PRs in 2 years 2 months
Contributions summary:Seunghwa primarily contributed to adding and modifying error handling mechanisms within the `raft` library. Their work involved importing and modifying error-handling-related header files and defining various macros to ensure correct execution and error reporting. The user added exceptions for CUDA, NCCL, cuSparse, and cuRAND errors and incorporated error-checking macros for CUDA, cuSparse, and NCCL API functions. These changes aimed to improve the robustness and debugging capabilities of the library.
sciencedata-sciencemachine-learninggraph-data-sciencefundamental
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.