HPC Research Scientist II

Posting Details

• Posting Number: S06554P
• Position Title:
  
  HPC Research Scientist II
• Functional
  
  Title:
  
  High Performance Computing Research Scientist II
• Department:
  High Performance Computing
• Salary Range: $115,000 - $140,000 DOQ
• Pay Basis:
  Monthly
• Position Status:
  Regular full-time
• Location:
  
  Richardson
• Posting Open Date: 08/11/2025
• Open Until Filled:
  Yes
• Desired
  
  Start Date:
  
  09/01/2025

The High-performance Computing (HPC) Research Scientist will be responsible for guiding customers using complex research computing resources for advanced research purposes. The position will provide leadership in consulting, technical support, and training to users of high-performance computing resources. Responsibilities include leading customers through onboarding on HPC systems; porting, debugging and optimizing code; troubleshooting and providing general assistance in using HPC systems;

training faculty and students on use of HPC resources and parallel programming; and tracking the use of HPC resources and the resulting research outcomes and publications. Overall, the position provides leadership and guidance on facilitation services and reports to the Director of HPC Facilitation.

A minimum of a PhD in a field directly related to research and a minimum of two years of experience/expertise as noted below.

• PhD in Computer Science, engineering, science, Mathematics, Data Science or similar quantitative subject areas.
• Expert knowledge of HPC systems, best practices, and research customer support.
• Ability to troubleshoot customer code, porting code, and optimizing code for HPC environments.
• Excellent interpersonal, written, and verbal communication skills are essential.
• Multitasking, ability to work with different teams and with varied customer needs.
• Ability to gather data about the use of HPC systems, analyze the data and prepare reports for leadership.
• Ability to manage support tickets and prioritize, considering varied scope, scale, and technical requirements.
• Ability to define, deliver, and optimize HPC or scientific support services.
• Know multiple programming and scripting languages.
• Extensive knowledge of parallel programming techniques, including shared memory and message passing parallel programming, and knowledge of GPU programming.
• Experience with scientific computing code development and support.
• Knowledge of Linux usage, scripting, Git, development tools and an HPC batch processing system.
• Knowledge of containers (especially Apptainer), Open OnDemand, data modelling and data repositories.
• Experience in using HPC resources within a university or from national cyberinfrastructure resources.
• Previous work with faculty in research projects, worked with and mentored students, written and presented academic/research papers.
• Experience attending conferences, representing one's institution, and gleaning trends and opportunities in the field and industry.
• Demonstrated ability in writing grant papers, identifying opportunities for grants and converting them into grants.
• Demonstrated ability in presenting at conferences either as tutorials, lightning talks, or workshops.

• Ability to program in multiple programming languages like C/C++, FORTRAN, Python, R or similar scientific programming languages.
• Knowledge of parallel programming using the shared memory and message passing techniques. Knowledge of OpenMP and MPI or similar programming directives and libraries.
• Knowledge of GPU programming with CUDA, HIP, oneAPI or OpenMP for GPUs, Python Numba.
• Knowledge of general-purpose scientific libraries like BLAS, Num Py, CuPy, various mathematical, statistical and graphing libraries, Tensor Flow, PyTorch, Pandas, or similar widely used libraries.
• Knowledge of HPC job execution environments like SLURM, PBS, or similar. Knowledge of launcher and array jobs.
• Understanding of computer architecture elements that affect code performance, including instruction-level parallelism, multilevel caches, the memory hierarchy, distributed shared memory, high-speed IO, DMA/RDMA, code profiling hardware support, GPU architectures, SIMD programming, and elements of GPU streaming…