Andrew Mundy is a Staff Engineer at Arm with 13 years' experience translating research ideas into production-quality machine learning software and kernels for experimental computer architectures. He specializes in metaprogramming and code generation for high-performance GEMM and ML kernels, numerical improvements to fast convolution algorithms (Winograd), and mapping spiking neural networks and the Neural Engineering Framework onto massively parallel SpiNNaker hardware. His background blends a PhD in computer science with hands-on machine management and routing-compression techniques for constrained distributed machines, giving him unusual depth in both low-level optimization and system-scale mapping. Colleagues know him for squeezing accuracy and performance out of novel architectures and for turning complex neuroscience models into runnable, optimised systems.
13 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy (PhD), Computer Science, Doctor of Philosophy (PhD), Computer Science at The University of Manchester
BEng, Electrical & Electronic Engineering, 1st Class (Hons), BEng, Electrical & Electronic Engineering, 1st Class (Hons) at University of Newcastle-upon-Tyne
Contributions:6 releases, 185 PRs, 521 pushes in 2 years 1 month
simulatorsimulationnengospinnakerneural-networks
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.