Matthew Jones
Senior Software Engineer at NVIDIA
Longmont, Colorado, United States
Summary
🤩
Rockstar🎓
Top SchoolMatthew Jones is a Senior Software Engineer at NVIDIA with a decade of experience building high-performance GPU software, currently focused on cuQuantum to bring GPU-accelerated primitives to quantum simulation frameworks. He blends deep scientific training (PhD-level physics) with practical systems engineering, having accelerated end-to-end research pipelines across Python, C/C++, Fortran, RAPIDS, and the NVIDIA HPC SDK. Matthew has a strong track record in performance-critical back-end work—contributing to widely used RAPIDS projects like cuDF and cuML on concurrency, hash-joins, and CUDA kernel optimizations. He’s as comfortable designing scalable libraries as he is diving into low-level concurrency and data-movement details that unlock real-world speedups. Based in Longmont, Colorado, he’s motivated by enabling novel scientific applications through GPU computing and quantum simulation.
10 years of coding experience
4 years of employment as a software developer
Bachelor of Applied Science (B.A.Sc.) Engineering Physics/Applied Physics, Bachelor of Applied Science (B.A.Sc.) Engineering Physics/Applied Physics at Colorado School of Mines
English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (22)
c-language10
python10
machine-learning10
data-structure10
gpu10
hashtable10
data-structures10
cuda10
cprogramming-language10
concurrency10
machine-learning-algorithms9
data-analysis9
numba9
arrows7
arrow-keys7
Programming languages (6)
Github contributions (5)
rapidsai/cudf
Jul 2018 - Oct 2020
cuDF - GPU DataFrame Library
Role in this project:
Back-end Developer
Back-end DeveloperContributions:13 reviews, 53 commits, 13 PRs in 2 years 3 months
Contributions summary:Matthew's commits focus on modifications within the `cudf` library, specifically related to concurrency and hash-join operations, indicating a focus on performance-critical backend components. The user made changes to the `concurrent_unordered_multimap.cuh` file, suggesting an involvement with concurrent data structures. Furthermore, the contributions include changes related to casting and data type transformations, implying involvement in data processing and manipulation tasks.
cudadataframe-librarydata-analysiscppcudf
rapidsai/cuml
Mar 2019 - Mar 2019
cuML - RAPIDS Machine Learning Library
Role in this project:ML Engineer
ML EngineerContributions:19 commits, 1 PR, 3 comments in 1 day
Contributions summary:Matthew primarily focused on improving the `numba_utils.row_matrix` function within the cuML library. These updates involved refactoring the implementation to support arbitrary data sizes, enhancing the efficiency of data transfer using CUDA, and modifying the kernel logic. Several commits involved style improvements and code cleanup. Further, the user merged in changes from branch-0.6, and modified CMake and build script settings to include OpenMP and OpenBLAS.
cudacumlnvidiadata-sciencegpu
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.