Michael Potter
Senior Navigation Engineer
Somerville, Massachusetts, United States
Summary
👤
Senior🎓
Top SchoolMichael Potter is a Ph.D. candidate and data scientist who designs uncertainty-aware Bayesian ML systems for mission-critical healthcare and defense applications, with eight years of experience translating research into production. He built the U.S. Navy’s first Bayesian neural network for missile reliability, led NLP and MLOps efforts that saved engineering time and earned peer recognition, and won the IEEE RAMS Best Paper award. His research spans probabilistic temporal models—Bayesian Hawkes, survival analysis, and recursive fusion—to predict human behavior and optimize radar/trajectory planning, often improving accuracy while quantifying confidence. Comfortable in Python, JAX, PyTorch and NumPyro, he pairs rigorous Bayesian inference with practical pipelines and has a track record of securing research funding and deploying models in operational settings. An unexpected throughline: he applies tools honed on weapon-system reliability to sensitive health problems like forecasting aggression in youth with autism, emphasizing actionable uncertainty for safer decisions.
8 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy - PhD, Electrical and Electronics Engineering, Doctor of Philosophy - PhD, Electrical and Electronics Engineering at Northeastern UniversityUniversity of California, Los Angeles
Github Skills (65)
lstm10
time-series-forecasting10
visualization9
time-series9
inference-engine9
optical-flow9
bayesian9
transformer8
ai-agent8
action-recognition8
ontology7
gpu7
robustness7
deep-learning7
scikit7
Programming languages (6)
Github contributions (5)
mlpotter/DeepKoopmanLusch
Apr 2022 - Jan 2023
PyTorch Implementation of Lusch et al DeepKoopman
Contributions:22 commits, 15 pushes, 1 branch in 8 months
pytorch
yashlala/attentive-session-based-recs
Apr 2021 - Nov 2021
CS 249 Project.
Contributions:72 commits, 59 pushes, 1 branch in 6 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.