Wonchan Lee
Principal Software Engineer at NVIDIA
California, United States
Summary
🤩
Rockstar🎓
Top SchoolWonchan Lee is a Principal Software Engineer with 14 years of experience, currently leading GPU-focused systems and backend development at NVIDIA from California. With a Ph.D. in Computer Science from Stanford and prior research roles at Stanford and Los Alamos, he blends deep research rigor with production-grade engineering. He has a strong track record improving high-performance data tooling—contributing substantive fixes to the notable rapidsai/cudf GPU DataFrame library around memory resource management, asynchronous stream handling, and hashing stability. Known for surfacing subtle correctness and performance issues, he bridges low-level systems work and practical developer-facing APIs. His background includes industry internships at NVIDIA and AMD, reflecting longstanding focus on accelerating data processing on modern hardware.
14 years of coding experience
15 years of employment as a software developer
M.S. Electrical Engineering and Computer Science, M.S. Electrical Engineering and Computer Science at Seoul National UniversityDoctor of Philosophy (Ph.D.) Computer Science, Doctor of Philosophy (Ph.D.) Computer Science at Stanford University
Korean, English
Github Skills (13)
cuda10
memory-management10
cudf10
hash-functions10
c-language10
parallel-computing10
cprogramming-language10
gpu10
dataframe9
data-structure9
cpp9
data-structures9
dataframes9
Programming languages (10)
Github contributions (5)
NVIDIA/cudf
Apr 2020 - Apr 2021
cuDF - GPU DataFrame Library
Role in this project:
Back-end Developer
Back-end DeveloperContributions:10 reviews, 31 commits, 17 PRs in 11 months
Contributions summary:Wonchan primarily focused on improving the `cudf` GPU DataFrame library, specifically addressing memory resource management, stream handling, and fixing potential bugs. Their contributions include correct usage of user-provided memory resources in join operations, fixing issues related to hashing, and passing streams for asynchronous operations. They also refined mask allocation policies and addressed issues in various functionalities like shift and copy operations, ensuring better performance and stability of the library.
cudfdataframegpurapidsarrow
nv-legate/legate.pandas
Apr 2021 - Jul 2021
An Aspiring Drop-In Replacement for Pandas at Scale
Contributions:33 commits, 7 PRs, 13 pushes in 2 months
pandas
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.