Postdoctoral Associate-Nuclear Multiphysics Data Analytics

Oak Ridge National Laboratory
Oak Ridge, Tennessee 37831
  • Job Type
    Employee
  • Job Status
    Full Time

Purpose

Seeking an outstanding, highly motivated post-doctoral associate with demonstrated technical skills and capabilities in the field of machine learning (ML) with applications to solving complex problems arising in the nuclear engineering focus areas of the Oak Ridge National Laboratory (ORNL) Advanced Reactor Engineering Group.

 

Major Duties / Responsibilities

 

  • Develop and apply ML methods to high-fidelity computational models. Use statistical inference and ML techniques to derive improved reduced-order models (ROMs) and/or reduced-fidelity models (RFMs).
  • Enable physics-based or physics-informed ML methods on leadership computing facility platforms to capture complex phenomena in nuclear systems without explicitly modeling the dynamic behavior.
  • Expand on the existing research by implementing this emerging technology to include physics domains, particularly reactor physics (neutronic/gamma transport and isotopic transmutation), thermal hydraulics, chemistry (thermodynamics and surface interactions), and multispecies mass transport in a multiphysics modeling and simulation framework, leveraging the expertise of ORNL analysts, modelers and software developers.

Requirements

Qualifications Required

 

  • PhD degree in nuclear engineering, mechanical engineering, electrical engineering, computer engineering, engineering physics, computational science, or a related field. Applicants cannot have received the most recent degree more than five years prior to the date of application and must complete all degree requirements before starting their appointment.
  • Documented experience in application of ML methods such as the convolution of neural networks to physical problems.
  • Strong background in standard convex optimization methods for training of specific ML models.
  • Demonstrated problem-solving skills, a willingness to apply those skills to a variety of engineering problems, and a proven aptitude in the application and deployment of ML methods to solve engineering problems on various platforms.
  • Excellent verbal communication, presentation, and writing skills to enable effective interaction with technical peers, program managers, and sponsors.
  • An excellent scholarly record demonstrating independence and initiative.
  • Ability to work independently and in a team environment, with experts from many disciplines
  • This position requires access to technology that is subject to export control requirements. Successful candidates must be qualified for such access without an export control license

 

Qualifications Desired

 

  • Strong theoretical understanding of computational learning, with specific background in probability theory and statistics. For instance, understanding of complexity of a function class, and its application to theoretical guarantees on ML model performance will be important skills.
  • Specific application experience in physics-based data-driven methods.
  • Ability to quickly comprehend the complexities of the governing equations and the data structures of each individual physics domain and to apply the appropriate ML methods to create reduced-order representations.
  • Demonstrated capacity to use and improve the ML tools on high performance computing platforms. These tools include, but are not limited to, TensorFlow, pyTorch and Keras.
  • Experience demonstrating the performance and limitations of a developed capability through uncertainty quantification and/or sensitivity analysis.

 

 

 

 

 

This position will remain open for a minimum of 5 days after which it will close when a qualified candidate is identified and/or hired.

We accept Word (.doc, .docx), Adobe (unsecured .pdf), Rich Text Format (.rtf), and HTML (.htm, .html) up to 5MB in size. Resumes from third party vendors will not be accepted; these resumes will be deleted and the candidates submitted will not be considered for employment.


If you have trouble applying for a position, please email ORNLRecruiting@ornl.gov.


ORNL is an equal opportunity employer. All qualified applicants, including individuals with disabilities and protected veterans, are encouraged to apply.  UT-Battelle is an E-Verify employer.

Categories

Before you go...

Our free job seeker tools include alerts for new jobs, saving your favorites, optimized job matching, and more! Just enter your email below.

Share this job:

Postdoctoral Associate-Nuclear Multiphysics Data Analytics

Oak Ridge National Laboratory
Oak Ridge, Tennessee 37831

Join us to start saving your Favorite Jobs!

Sign In Create Account