Bradley Dice
Senior Software Engineer In GPU-Accelerated Data Analytics
Kansas City, Missouri, United States
Summary
🤩
Rockstar🎓
Top SchoolBradley Dice is a Senior Software Engineer on NVIDIA’s RAPIDS team who builds high-performance, GPU-accelerated data analytics libraries (notably cuDF) using CUDA, modern C++, and Python. With a PhD in Physics and Scientific Computing from the University of Michigan and 13 years of engineering experience, he bridges scientific research and production-grade tooling, contributing to core projects like Numba, RMM, cuML, cuGraph and RAFT. He combines low-level performance work—fixing CUDA compatibility, Thrust includes and IPC handling—with devops expertise in CI/CD and build systems to keep large open-source projects shipping smoothly. A long-time open-source maintainer (signac) and contributor to widely used projects, he’s as comfortable writing cross-join implementations as authoring documentation and automated testing workflows. Based in Kansas City, he brings a background in interdisciplinary science, distributed project leadership, and a history of deploying software from supercomputers to mobile devices. An NSF Graduate Research Fellow and MolSSI Software Fellow, he’s motivated by applying computation and simulation to real-world scientific and data problems.
12 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Physics and Scientific Computing, Doctor of Philosophy (Ph.D.), Physics and Scientific Computing at University of MichiganBachelor of Arts (B.A.), Physics, Chemistry, Mathematics, and Applied Critical Thought & Inquiry, Bachelor of Arts (B.A.), Physics, Chemistry, Mathematics, and Applied Critical Thought & Inquiry at William Jewell College
Stackoverflow
371reputation
3kreached
14answers
0questions
Github Skills (61)
algorithm10
thrust10
algorithms10
pytorch10
github-ci10
c-language10
gpgpu10
pytest10
python10
sphinx10
matplotlib10
llvm10
testing10
dataframes10
graph10
Programming languages (24)
Github contributions (5)
rapidsai/cudf
May 2020 - Jan 2023
cuDF - GPU DataFrame Library
Role in this project:
Back-end Developer
Back-end DeveloperContributions:5133 reviews, 357 commits, 433 PRs in 2 years 8 months
Contributions summary:Bradley's commits primarily focus on implementing and updating features related to data manipulation and analysis, specifically within a GPU DataFrame library. The changes involved adding a new feature to perform cross joins, and updating the implementation, along with adding tests and debugging to ensure correct behavior and performance. They also worked on improving the codebase's maintainability by addressing code style violations, correcting documentation and updating imports to support the development process.
cudadataframe-librarydata-analysiscppcudf
rapidsai/rmm
Jun 2020 - Jan 2023
RAPIDS Memory Manager
Role in this project:Back-end & DevOps Engineer
Back-end & DevOps EngineerContributions:555 reviews, 36 commits, 126 PRs in 2 years 7 months
Contributions summary:Bradley primarily contributed to improving the build process, documentation, and overall maintainability of the RMM library. Their work included fixing documentation formatting, updating pre-commit hooks, and adding support for Python 3.10. They also addressed issues with CUDA runtime versions and IPC handle support, demonstrating an understanding of the library's integration with CUDA and Numba. Moreover, the user focused on cleaning up Thrust includes and formatting the gdb script.
cudamemory-managementmemorycpppython
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.