James Newling
California, United States
Summary
🤩
Rockstar🎓
Top SchoolJames Newling is a software engineer and researcher with 11 years of experience specializing in AI, compiler development, and high-performance linear algebra implementations. He combines deep academic training (PhD-level work at EPFL and advanced mathematics from University of Cape Town and Ecole polytechnique) with practical contributions to ML accelerator toolchains and framework backends. His work spans graph algorithms, MLIR, C++, and Python, with hands-on experience integrating optimized GEMM routines—evidenced by contributions to AMD’s MIOpen to adapt tinygemm for matrix multiplication. Based in California, he bridges research and engineering to make sophisticated compiler and accelerator techniques production-ready. Colleagues appreciate that he moves comfortably between low-level performance tuning and higher-level ML framework concerns, often surfacing subtle numerical and geometric trade-offs.
11 years of coding experience
Honours, Mathematics and Statistics, Honours, Mathematics and Statistics at University of Cape TownMasters, Complexity Science, Masters, Complexity Science at Ecole polytechniqueDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at EPFL (École polytechnique fédérale de Lausanne)
Stackoverflow
624reputation
267kreached
4answers
5questions
Github Skills (13)
matrix-multiplication10
c-language10
cprogramming-language10
linear-algebra10
performance-optimization9
opencl9
machine-learning8
interrupt6
smart-pointers6
ipython6
python6
unique-ptr6
cython6
Programming languages (9)
Github contributions (5)
ROCm/MIOpen
May 2017 - Aug 2017
AMD's Machine Intelligence Library
Role in this project:
ML Engineer
ML EngineerContributions:39 commits, 4 comments in 2 months
Contributions summary:James's commits primarily involve modifications related to the integration of the tinygemm library within the MIOPEN framework. This includes adapting existing gemm geometry and related functions to align with tinygemm's API and structure. The contributions focused on ensuring the correct use of tinygemm for matrix multiplication, particularly within the context of AMD's Machine Intelligence Library. These changes likely aimed to improve the performance or integration of optimized matrix operations within the library.
amdcluster-computingmachine-learningblasmachine-intelligence
newling/iree
Oct 2023 - Apr 2025
Contributions:29 pushes, 13 branches in 1 year 5 months
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.