Damian Owerko is a research scientist and PhD-trained electrical and systems engineer with nine years of experience applying machine learning and graph signal processing to socially impactful problems like electrical grid optimization. He blends deep learning, GNNs and signal-processing expertise to produce practical gains—his work at UPenn yielded a 5% cost reduction in grid operations and sub-2% error rates, and a multi-sensor tracking system that improved accuracy by 40% over prior art. A hands-on collaborator with industry partners (Lockheed Martin, Apple, Meta) and polished presentation experience—including briefing Congress—he moves ideas from research to real-world deployment. He has published multiple IEEE conference papers and developed scalable training strategies such as transfer learning from small scenarios to large systems. Known for designing reproducible experiments and tooling (PyTorch, Dask, C++ integrations), he balances theoretical rigor with engineering pragmatism. Based in Philadelphia, he combines multidisciplinary training in robotics, physics and systems engineering with a knack for turning signal-processing theory into operational improvements.
9 years of coding experience
4 years of employment as a software developer
High School, High School at American School of Warsaw
High School, HL: Physics, Math, Economics; SL: Chemistry, Spanish, English, 44, High School, HL: Physics, Math, Economics; SL: Chemistry, Spanish, English, 44 at Sevenoaks School, Sevenoaks, United Kingdom
Doctor of Philosophy - PhD, Electrical and Systems Engineering, 4.0, Doctor of Philosophy - PhD, Electrical and Systems Engineering, 4.0 at University of Pennsylvania
Contributions:1 review, 4 PRs, 171 pushes in 3 years 2 months
deep-learningpytorchconstrainedmachine-learning
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.