Postdoc in Machine Learning for Monte-Carlo Methods at Oak Ridge National Laboratory

End Posting Date: 02/17/2018 

Purpose: 

The National Center for Computational Sciences (NCCS) within the Computational Sciences Directorate at the Oak Ridge National Laboratory (ORNL) is seeking to fill a postdoctoral position for development and application of novel, scalable machine learning methods to accelerate Monte-Carlo calculations for scientific computing. This position will involve collaboration between researchers in the National Center for Computational Sciences, the Computer Science and Mathematics Division, and the Materials Science and Technology Division. This project is situated at the fertile interface of computational science, stochastic simulation, machine learning, and materials science. 

Major Duties/Responsibilities: 

The applicant will join the effort to explore new applications of data analytics and machine learning methods to accelerate scientific computing. The aim of this project is to combine machine learning with Monte-Carlo sampling techniques to reduce the computational effort required for Monte-Carlo moves when sampling functions are expensive to evaluate (e.g. ab initio energies in chemistry and material physics applications). The applicant will develop and implement machine learning methods for these scientific computing problems and evaluate their performance. The candidate will have the opportunity to use the ORNL leadership computing facility to apply and extend these methods to the calculation of material properties that are currently inaccessible to most existing ab initio codes. 

The candidate will collaborate with others to maintain a high level of scientific productivity. The candidate will be responsible to report the research results in key peer-reviewed journals and at scientific conferences in a timely manner. 

This position will reside in the Scientific Computing Group at the National Center for Computational Sciences. The postdoctoral associate will interact with a variety of researchers developing and applying state-of-the-art machine learning and Monte-Carlo methods. 

Qualifications Required: 

Basic Requirements: 

• This position requires a Ph.D. in Applied Mathematics, Statistics, Computer Science, Physics, Chemistry, or a related field. 

• A strong background in the development, implementation and application of machine learning or Monte-Carlo methods. 

Preferred Qualifications: 

• Oral and written communication skills. 

• Experience in developing and programming for accelerators (e.g. GPUs) and parallel high performance computing architectures. 

• Experience in scientific computing for physics, chemistry or material sciences. 

• Programming experience in C++ and Python, particularly with parallel programming on large-scale facilities. 

The Ph.D. degree should have been earned no more than five years prior to the date of the application and all degree requirements must be complete before starting the appointment. 

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), Excel(.xls, .xlsx), PowerPoint(.ppt, .pptx), Adobe(.pdf), Rich Text Format(.rtf), HTML(.htm, .hmtl) and text files(.txt) up to 2MB 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

Notice: If the position requires a Security Clearance, reviews and tests for the absence of any illegal drug as defined in 10 CFR 707.4 will be conducted by the employer and a background investigation by the Federal government may be required to obtain an access authorization prior to employment and subsequent reinvestigations may be required. 

If the position is covered by the Counterintelligence Evaluation Program regulations at 10 CFR 709, a counterintelligence evaluation may include a counterintelligence-scope polygraph examination. 

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.