Paris Perdikaris
Associate Professor
Philadelphia, Pennsylvania, United States
Summary
👤
Senior🎓
Top SchoolParis Perdikaris is an Associate Professor and computational scientist with a decade of experience at the intersection of deep learning and physical modeling, currently based in Philadelphia. He develops foundation models for weather and climate, physics-informed neural networks, neural operators, and generative models, with a strong emphasis on uncertainty quantification for sequential decision-making in scientific and engineering settings. His career spans academic leadership at the University of Pennsylvania, postdoctoral work at MIT, and research management experience at Microsoft, reflecting a blend of fundamental research and applied systems thinking. Trained as an applied mathematician (PhD, Brown) with earlier engineering roots in naval architecture, he brings rigorous mathematical foundations to large-scale, physics-aware ML. Notably, his work aims to make AI models respect conservation laws and physical constraints—bridging theory and operational modeling in climate and engineering domains.
10 years of coding experience
9 years of employment as a software developer
Doctor of Philosophy - PhD Applied Mathematics, Doctor of Philosophy - PhD Applied Mathematics at Brown UniversityMaster’s Degree Naval Architecture and Marine Engineering, Master’s Degree Naval Architecture and Marine Engineering at National Technical University of Athens
English, Greek, Spanish
Github Skills (23)
supervised-learning9
gaussian9
gaussian-processes7
machine-learning6
python6
optimization5
gpu5
automatic-differentiation5
pytorch5
autodiff4
jit4
deep-learning3
composable3
jax3
numpy3
Programming languages (2)
Github contributions (5)
PredictiveIntelligenceLab/JAX-BO
Jul 2020 - Mar 2022
Contributions:51 commits, 7 pushes, 1 comment in 1 year 8 months
paraklas/GPTutorial
Jun 2017 - Nov 2019
A hands-on tutorial on supervised learning with Gaussian processes
Contributions:6 commits, 2 PRs, 4 pushes in 2 years 6 months
hands-onsupervised-learningsupervisedhandsmachine-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.