Argonne National Laboratory Postdoctoral Appointee - Accelerated Deep Learning Discovery in Fusion Energy Science in Lemont, Illinois

Postdoctoral Appointee - Accelerated Deep Learning Discovery in Fusion Energy Science

Requisition Number: 405449 Location: Lemont, IL

Functional Area: Research and Development Division: LCF-Leadership Computing Facility

Employment Category: Temporary 6 Months or Greater Education Required: Doctorate Degree

Level (Grade): 700 Shift: 8:30 - 5:00 Share: Facebook LinkedIn Twitter

The mission of the Argonne Leadership Computing Facility (ALCF) is to accelerate major scientific discoveries and engineering breakthroughs for humanity by designing and providing world-leading computing facilities in partnership with the computational science community. We help researchers solve some of the world’s largest and most complex problems with our unique combination of supercomputing resources and expertise.

We invite you to apply for a postdoctoral appointee position with the ALCF. You will research and develop a scientific workflow targeting our forthcoming exascale supercomputer, Aurora. The scientific purpose is to predict and ultimately mitigate large-scale major disruptions in tokamak fusion devices such as the forthcoming ITER machine now under construction, as well as existing and near-future devices. Deep learning methodology centers around a recurrent neural network, trained using experimental data (or, potentially, simulation data). Data from upcoming long-pulse, superconducting tokamaks should help increase the advanced disruption prediction capability of the RNN to a time frame appropriate for ITER. The position is with a project under ALCF’s Aurora Early Science Program, which combines the efforts of multi-institutional investigator teams with ALCF staff and Aurora vendor applications experts.

In addition to the project PI and extended project team, you will work with the Computational Science (Catalyst) and Data Science teams at ALCF. You will have a rare chance to learn and exploit some of the world’s largest supercomputers, and use state-of-the-art techniques on our current and next-generation supercomputing systems to help solve significant scientific problems.

Ideal candidates are expected to have:

  • PhD + 0-3 years in computational sciences including physics and engineering, or in a related field.
  • Comprehensive knowledge of numerical methods, parallel programming, machine learning/deep learning methods and frameworks.
  • Comprehensive experience programming in one or more programming languages such as C, C++, and Python.
  • Considerable knowledge of parallel algorithms, distributed memory architectures, and parallel performance evaluation of domain specific implementations.
  • Candidate should have the ability to create, maintain, and support high-quality software.
  • An ideal candidate would have published their scientific software in a public repository (e.g. GitHub).
  • Good communication skills both verbal and written.
  • Considerable independent judgment and critical thinking.

Desirable Knowledge and Skills

  • Considerable knowledge of (and experience with) magnetic fusion plasma physics, and the numerical methods applied in their simulation.
  • Considerable knowledge of (and experience with) machine learning/deep learning methodologies and software frameworks.
  • Expert level knowledge of (and experience with) Python.
  • Good experience and skills in interdisciplinary teams involving mathematicians, computer scientists, and discipline scientists.
  • Collaborative skills including the ability to work well with other laboratories and universities, supercomputer centers, and industry.
  • Good publication record, preferably including first-author publication(s).
  • Experience with scientific applications that scale to several thousand processes on massively parallel platforms.

As an equal employment opportunity and affirmative action employer, Argonne National Laboratory is committed to a diverse and inclusive workplace that fosters collaborative scientific discovery and innovation. In support of this commitment, Argonne encourages minorities, women, veterans and individuals with disabilities to apply for employment. Argonne considers all qualified applicants for employment without regard to age, ancestry, citizenship status, color, disability, gender, gender identity, genetic information, marital status, national origin, pregnancy, race, religion, sexual orientation, veteran status or any other characteristic protected by law.