The Princeton Plasma Physics Laboratory (PPPL) is seeking a research associate to develop machine learning algorithms for controlled nuclear fusion. PPPL is a world leading Department of Energy plasma physics laboratory focusing on fusion energy research and is managed by Princeton University. Machine learning is expected to play an integral role in plasma control systems in order to achieve stable plasma burn for fusion energy. This project will include the application of machine learning methods to predictive modeling of the evolution of the spherical tokamaks including NSTX-U and MAST-U, identification of constraints on the operating space, e.g., disruption limits, and optimization of actuator trajectories for planning experimental campaigns. The successful candidate will work with group members and collaborators to develop reduced/accelerated models of plasma behavior and approaches to optimize experiment performance within safe operating limits. The appointment will be based in Princeton.
The Princeton Plasma Physics Laboratory is a world-class fusion energy research laboratory managed by Princeton University for the U.S. Department of Energy’s Office of Science. PPPL is dedicated to developing the scientific and technological knowledge base for fusion energy. The Laboratory advances the fields of fusion energy and plasma physics research to develop the scientific understanding and key innovations needed to realize fusion as an energy source for the world.
The successful candidate will work to develop machine learning accelerated approaches for plasma equilibrium and profile evolution in DIII-D discharges. The candidate will use these models to develop simulators and performance optimization strategies. Relevant methods include deep learning, numerical optimization including genetic algorithms and Bayesian optimization, dynamic systems modeling, and control theory. The methods will be tested first in simulations and those that are successful will be tested on real devices.
We are looking for a highly motivated data scientist and an excellent communicator who will collaborate closely with the onsite team at PPPL and collaborators at MAST-U.
The successful candidate will be based in Princeton and is expected to occasionally travel to MAST-U in the UK (1-2 trips per year) as well as workshops and conferences.
Education and Experience:
- Applicants should have a Ph.D. in data science, control engineering, plasma physics, or related fields
- Preference will be given to candidates with experience in tokamak physics, machine learning for dynamic systems, and optimization
- Familiarity with machine learning approaches for modeling complex time-dependent, spatially distributed systems is required
- Experience with optimization, and/or control algorithm design is desired
- Excellent software development skills in Python and/or C/C++, MATLAB/Simulink
- Excellent presentation, writing, and communication skills
- Familiarity with parallel computing, high-performance computing, and software development tools
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
Please be aware that the Department of Energy (DOE) prohibits DOE employees and contractors from participation in certain foreign government talent recruitment programs. All PPPL employees are required to disclose any participation in a foreign government talent recruitment program and may be required to withdraw from such programs to remain employed under the DOE Contract.
