Nathan Perkins is a Machine Learning Engineer in Cambridge, MA with 13 years of experience bridging computational neuroscience, embedded imaging, and production software. He developed minimally invasive, multichannel microfiber interfaces and low-latency audio/video pipelines to enable head-mounted microscopy and basic brain–machine interfaces, then translated that research mindset into ML work at Apple. Nathan combines rigorous academic training (PhD in Computational Neuroscience, MS from MIT) with full-stack engineering instincts honed founding and running product companies that serve thousands of users monthly. He is an active contributor to neuroimaging tooling—improving Nipype preprocessing—and has strengthened robustness in widely used SDKs like Mailgun’s PHP client. Colleagues rely on him to move complex experimental systems from prototype to reliable pipelines that operate at low latency and real-world scale.
13 years of coding experience
14 years of employment as a software developer
BA, Neuroscience, Law and Society, Thematic Approaches to Humanities and Society, BA, Neuroscience, Law and Society, Thematic Approaches to Humanities and Society at University of Southern California
Master of Science (M.S.), ESD Technology and Policy, Master of Science (M.S.), ESD Technology and Policy at Massachusetts Institute of Technology
Doctor of Philosophy - PhD, Computational Neuroscience, Doctor of Philosophy - PhD, Computational Neuroscience at Boston University
Contributions:5 commits, 1 comment, 1 issue in 5 years 3 months
Contributions summary:Nathan contributed to the Mailgun PHP SDK by adding and enhancing error handling. They added properties to the `GenericHTTPError` exception to include response code and body details. The user revised domain creation by allowing select arguments and adding validation. They also added new tests to the domain creation flow, improving the robustness of the SDK.
Workflows and interfaces for neuroimaging packages
Role in this project:
Data Scientist
Contributions:5 commits, 2 PRs, 5 comments in 11 days
Contributions summary:Nathan primarily contributed to preprocessing scripts within the Nipype neuroimaging workflow library. Their work involved removing redundant columns from motion regressors, ensuring the correct data type for bandpass frequency arguments, and updating preprocessing scripts for resting-state fMRI analysis. These changes were aimed at improving the accuracy and efficiency of data analysis pipelines within the neuroimaging context. The user also refactored preprocessing scripts to use linear interpolation.
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.
Request Free Trial
Nathan Perkins - Machine Learning Engineer at Apple