Princeton Plasma Physics Laboratory seeks to fill a theoretical postdoctoral research position focusing on applying machine learning (ML) and data analytic techniques to extreme-scale physics simulations run on high-performance computers. The large data sets generated by these simulations require new ways to handle and analyze in order to maximize the insight gained. Additionally, code acceleration and workflow automation/optimization are constant goals. Machine learning and associated algorithms hold promise to contribute to these goals. This postdoctoral position may research various applications of ML to codes in the High-Performance Boundary Plasma Simulation (HBPS) SciDAC project, including: optimization of input parameters, generative models for turbulence data in transport-scale simulations, preconditioner tuning, object recognition (e.g. blob detection/tracking), unsupervised pattern and structure discovery, etc.
The ideal candidate will have a strong applied mathematics and computational background. Strong coding skills in languages such as Fortran and Python are highly recommended. Previous experience applying machine learning to research problems is encouraged. Experience with magnetic confinement fusion theory or experiment is a plus. Ph.D. degree in physics, mathematics, computer science or in engineering is required.
Qualified applicants should apply at www.pppl.gov and send a curriculum vitae and bibliography, and arrange to have at least two letters of recommendation sent as soon as possible for full consideration.
Letters can be mailed to Dr. C.S. Chang, Princeton Plasma Physics Laboratory, James Forrestal Campus, P.O. Box 451, Princeton, NJ 08543 or emailed to email@example.com.
Princeton University is an Equal Opportunity/Affirmative Action Employer and all qualified applicants will receive consideration for employment without regard to age, race, color, religion, sex, sexual orientation, gender identity or expression, national origin, disability status, protected veteran status, or any other characteristic protected by law. EEO IS THE LAW