Cathal Corbett
Senior Software Engineer at Arm
Galway City, Connacht, Ireland
Summary
👤
Senior🎓
Top SchoolCathal Corbett is a Senior Software Engineer based in Galway with four years of hands-on experience building machine learning compilers and GPU compute software at Arm. He progressed from graduate work on the open-source Arm NN and Android NN Driver to shipping production-facing ML and Mali DDK features, demonstrating a strong grounding in both research-grade HPC and embedded/accelerated inference. Skilled in improving robustness and test coverage, his open-source contributions include fixes and unit tests to prevent crashes in Arm NN FullyConnected layers—an attention to detail that reduces runtime errors in ML deployments. He holds a Master's in High Performance Computing with Data Science from the University of Edinburgh and brings practical HPC experience from a PRACE summer project monitoring Slurm job queues. Known as a self-starter with clear communication skills, he blends low-level systems engineering with a pragmatic focus on reliability and performance.
4 years of coding experience
2 years of employment as a software developer
Master's degree, High Performance Computing with Data Science, Master's degree, High Performance Computing with Data Science at The University of EdinburghBachelor's Degree, Computer Science and Information Technology., Bachelor's Degree, Computer Science and Information Technology. at National University of Ireland, Galway
Github Skills (6)
neural-network10
unit-testing10
machine-learning10
c-language10
cprogramming-language10
python3
Programming languages (2)
Github contributions (5)
ARM-software/armnn
Oct 2021 - Jan 2023
Arm NN ML Software. The code here is a read-only mirror of https://review.mlplatform.org/admin/repos/ml/armnn
Role in this project:
ML Engineer
ML EngineerContributions:83 commits, 38 comments, 10 issues in 1 year 3 months
Contributions summary:Cathal's commits focused on enhancing the Arm NN ML Software, specifically concerning the FullyConnected API. They added error checking, unit tests, and improved the descriptive messaging for FullyConnected layers. Code changes included the creation of new methods and unit tests to catch cases where weights or bias are not set correctly in FullyConnected layers, addressing potential crashes.
adminarmv8deep-learningneural-networksmachine-learning
ARM-software/android-nn-driver
Oct 2021 - Dec 2022
Contributions:8 commits in 1 year 1 month
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.