Postdoctoral Fellow at UCAR – Mesa Lab Building

Postdoctoral Fellow I at UCAR – Mesa Lab Building, United States

Job Description

Summary:

NSF | NCAR is excited to announce a job opening for a Postdoctoral Fellow I role. This position is focused on the evolution of high-performance computing (HPC) scientific codebases. The incumbent works on developing techniques to accelerate the transition of existing legacy applications to utilize modern language-based approaches based on C++ or Python. This applied research is focused on an alternative to a directive-based approach to GPU enablement and may include leveraging C++ productivity frameworks, Domain-Specific Languages, and other alternative programming languages.

The developed solutions must provide a performance portable solution across an array of both CPU and GPU architectures. This position, which is funded under the Community Software Facility project with pre-defined research goals, is directed by an NSF NCAR staff member and will involve collaboration with the Edinburgh Parallel Computing Centre (EPCC).

Visa Sponsored Job:
Yes

Relocation Assistance Eligible:
Yes

Job Location:

Boulder, Colorado

Position Type & Term:
Full time, Term – 6 months or more (Fixed Term)

Compensation Range:
Salary Annual Rate: $80,480
* * Final salary and rates are based on education, experience, skills relevant to the role.

Final date to receive applications:
This position will be posted until 11:59 PM MDT, Friday, May 9, 2025.

Required application materials: (preferably in PDF Format)

• Resume
• Cover Letter – Please address how your skills and experience meet the needs of this position (for more information, please refer to the Key Responsibilities and Knowledge, Skills, and Abilities sections of this job posting). Please also describe a recent important project you have been working on.

Background Checks:
Conducted for candidates selected for hire. Learn more .

Work Location:

Regardless of flexible work arrangements, UCAR requires ALL positions to be performed within the U.S., excluding U.S. Territories.

Please note that this position is intended as HYBRID, w/ a minimum requirement of 3 days/week onsite in Boulder, CO.

Here is a brief summary of what one would expect to be generally responsible for in this role.

• Design and implement methodologies that ensure software solutions can deliver optimal performance across a variety of hardware and software environments.
• Transition and optimize legacy CPU-based Fortran code to modern GPU-enabled architectures.
• Collaborate with researchers using LLM to explore the use of automated techniques for code transformation, optimization, and parallelization.
• Presents results at project meetings and conferences; publishes results in the peer-reviewed scientific literature and reviews scientific manuscripts.
• Contribute to team meetings and discussions, general coordination with the research team.
• Mentors students, interns, and visitors in collaboration with other NSF NCAR team members.

• Prioritize research and show independence in problem-solving once a project is underway.
• Seek help from other research team members when individual progress is hindered.
• Initiate meetings with mentors and other members of the research team when appropriate.
• Leads distillation and organization of results for presentation and publication in scientific journals.

Successful candidates will ensure their application materials speak to the following criteria:

• Ph.D. in computer science, atmospheric science, physics, engineering, or other relevant science.

• Skilled in high-performance parallel computing on both CPU and GPU architectures.
• Proficiency in applying modern computational frameworks written in C++ or Python to support efficient execution on both CPU and GPU architectures.
• Experience with the use of small-scale scientific mini-apps to evaluate program language approaches.
• Strong oral and written communication skills with demonstrated success publishing in peer-reviewed journals and/or computer science conferences.
• Ab…