Computational Scientist Artificial Intelligence Science; AIScience

Overview

The Princeton Plasma Physics Laboratory (PPPL) seeks to fill a Computational Scientist in Artificial Intelligence For Science (AI4

Science) position in the Computational Sciences Department. The successful candidate will establish and solicit long‑term funding for a program focused on (a) foundational research in Artificial Intelligence and Machine Learning (AI/ML), and (b) application‑oriented research in PPPL‑relevant AI4

Science topics. This is a leadership position that will strongly align with the Genesis Mission – a new initiative in AI/ML for Science that has been launched by the Department of Energy (DOE). The incumbent will develop a fast‑paced AI/ML program strategically aligned with DOE and other Federal Agency goals, ensuring that the research program advances and fits within PPPL Annual Laboratory Plans (ALP) goals.

Artificial Intelligence for Science and Energy represents a fundamental change in the scientific enterprise and an opportunity to provide foundational capabilities upon which to broaden PPPL’s mission. The incumbent will build new capabilities in the Computational Sciences Department to leverage this once‑in‑a‑generation opportunity to build an AI4

Science research program cifically, the incumbent will address the emerging need for AI/ML in fusion, other areas of plasma physics, and computational sciences. In addition, the incumbent will work with CSD Leadership to make key hires, build core research capabilities (including training of existing staff), and design a research program to discover new methods in data assimilation, experimental prediction, control systems, and solutions to partial differential equations.

To establish and solicit long‑term funding for a program focused on (a) foundational research in Artificial Intelligence and Machine Learning (AI/ML), and (b) application‑oriented research in PPPL‑relevant AI4

Science topics.

The Computational Sciences Department at PPPL was formed to provide a focus for computational physics and engineering. We specialize in algorithms and applied mathematics, data science and learning, high‑performance computing, multiscale integrated modeling, and software technology. While our current strengths reflect the traditional focus of the Laboratory on magnetic confinement fusion (MCF), with funding from the Department of Energy’s offices of Fusion Energy Sciences and the Advanced Scientific Computing Research, PPPL has always had a broad and healthy research program in areas other than MCF, including developing the theoretical and computational foundations of the dynamics and thermodynamics of naturally occurring plasmas, and more recently, in AI/ML and AI4

Science.

The successful candidate will help develop the laboratory’s effort in AI/ML and AI4

Science, collaborating with CSD leadership and other laboratory divisions. The candidate will help establish partnerships with Princeton University and other DOE National Laboratories. The candidate will assist in recruiting new team members, seek and secure funds to support the laboratory team, and present and publish original research in this general area. The present position comes with steady‑state funding for three years.

We are looking for candidates who can build a strong research program in one or more of the following topics:

Core Duties:

• 50% delivering on projects (AI research)
• 30% defined research
• 20% writing proposal building critical mass

• Ph.D. in Computer Science, Mathematics, Applied Mathematics, or a related field with core training in foundational & applied aspects of AI/ML.

• Minimum 15 years of professional experience in an academic, scientific, or R&D environment.
• A proven track record of publishing original results in peer‑reviewed scientific journals.
• Demonstrated scientific leadership and collaboration experience.

• Machine Learning for Digital Twins, Foundation Models, and surrogates.
• Inference tools for interpretive analysis of experimental and simulation data.
• Foundational research in Machine Learning for partial differential equations (PDEs).
• Innovative algorithmic and methodological approaches to AI‑augmented HPC…