Postdoctoral Research Associate - Scientific Machine Learning

Requisition Id 13290 

Overview: 

As a U.S. Department of Energy (DOE) Office of Science national laboratory, ORNL has an extraordinary 80-year history of solving the nation’s biggest problems. We have a dedicated and creative staff of over 6,000 people! Our vision for diversity, equity, inclusion, and accessibility (DEIA) is to cultivate an environment and practices that foster diversity in ideas and in the people across the organization, as well as to ensure ORNL is recognized as a workplace of choice. These elements are critical for enabling the execution of ORNL’s broader mission to accelerate scientific discoveries and their translation into energy, environment, and security solutions for the nation.

 

The Mathematics in Computation (MiC) Section at The Oak Ridge National Laboratory (ORNL) invites outstanding candidates to apply for a 2 year post-doctoral opportunity in mathematics/statistics and scientific computing with a strong emphasis on scientific machine learning on probabilistic dynamics applications.

 

This job offers an excellent opportunity to conduct exceptional and innovative research in mathematics, statistics and scientific computing, for applications with scientific and national priority.

 

ORNL’s mathematics research efforts provide the fundamental mathematical methods and algorithms needed to model complex physical, chemical, and biological systems. ORNL’s computational science research efforts enable scientists to efficiently implement these models at the extreme scale of computing and to store, manage, analyze, and visualize the massive amounts of data that result. ORNL’s artificial intelligence research provides the techniques to link the data producers, e.g., supercomputers and large experimental facilities, with the data consumers, i.e., scientists who need the data.   

 

The selected individual will join a team that is developing probabilistic and ensemble machine learning methods

for foundational AI models in massively networked dynamics problems. The junior scientist will also  participate in several on-going research projects across the lab, will  have access to advanced computer architectures and high performance machines (such as Frontier), and have first-hand opportunities to facilitate technology transfer from the laboratory research environment to industry and academia. MiC has a strong mentoring culture that provides junior scientists career and research guidance.

 

Major Duties and Responsibilities:

• Conduct leading-edge research in Scientific Machine Learning (SciML) on probabilistic dynamics applications.
• Interact with a diverse set of colleagues from both your own field, applications specialists, and others
• Work towards publishing new developments in high-profile peer-reviewed scientific journals or refereed conference proceedings; contribute to development of open-source software for high performance computing environments
• Travel as needed to support projects

 

Basic Qualifications:

• A PhD in mathematics, statistics, physics, computer science, engineering, or a related field completed within the last 5 years.
• Familiarity with Scientific Machine Learning (SciML), as evidenced by either completion of a graduate class that covered SciML or use of SciML in a research setting.
• Software development experience in C++ and Python. Familiarity with parallel programming, including experience developing MPI codes and programming GPUs.
• Research experience as evidenced by presentations, technical publications, released software and/or work with applications.

 

Preferred Qualifications:

• Extensive background in theoretical and applied probability, statistical physics, theoretical statistics, foundational aspects of data science or artificial intelligence.
• Experience in computational science and computational modeling.
• Experience with physics-informed deep learning.
• Passion around applying machine learning and computational methods to problems in science and engineering with experience solving prob