HPC Computational Scientist

Position Overview

We are looking for a driven and experienced HPC Computational Scientist to join our team. The individual will play a key role in supporting the compilation, execution, debugging, and optimization of in-house developed software on high-performance computing (HPC) infrastructures such as Shaheen III CPUs and GPU partitions.

Key Responsibilities

• Provide comprehensive assistance to users of laboratory HPC systems and related software applications.
• Support research and enable projects in computational science, engineering, big data analytics, artificial intelligence, machine learning, or related disciplines using KSL HPC infrastructure.
• Offer expertise in HPC application and library installation, porting, performance tuning, and optimization for both CPU and GPU platforms.
• Create, update, and deliver training resources, user guides, and internal documentation.
• Develop software tools and HPC applications that facilitate research conducted on KSL HPC clusters and supercomputing resources.
• Collaborate closely with faculty, researchers, and both academic and industrial partners to help achieve research goals within joint projects.
• Respond promptly and effectively to support inquiries via phone, walk-in visits, email, and ticketing systems.
• Maintain high standards of customer service when addressing user problems and questions.
• Install, port, and fine-tune high-performance software applications, tools, and data analysis software stacks.
• Keep current with scientific and technical advances through collaboration, training, conferences, and self-study.
• Stay up-to-date on the latest computing technologies and assist in benchmarking for future laboratory hardware purchases.
• Draft and review documentation related to systems, software testing, and installation.
• Provide individual and group instructional sessions on topics relevant to HPC users.
• Develop software tools and parallel application libraries as necessary for research support on cluster systems.
• Create software application benchmarks to assist with system upgrades.
• Pursue research aligned with laboratory objectives and personal interests; contribute to publications and presentations; engage in scientific communication and outreach.

Required Competencies

• Expert knowledge in computational science and engineering, data analytics, and artificial intelligence applications within HPC setups.
• Proven track record of supporting research within HPC environments.
• Ability to collaborate effectively in research-centric team environments.
• Experience programming HPC applications and tools using languages and frameworks like Fortran, C/C++, Python, MPI, OpenMP, CUDA, and OpenACC.
• Published research in computational science, engineering, or data analysis venues.
• Strong initiative, responsiveness, and team collaboration skills.
• Excellent analytical, problem-solving, and decision-making abilities.
• Innovative thinker with creativity in approach.
• Global perspective and organizational awareness.
• Ability to deliver superior quality work within deadlines.
• Strong planning and organizational skills.
• Familiarity with core concepts and best practices in the relevant domain.
• Knowledge of project management principles and practices.
• Capability to handle multiple projects simultaneously.
• Experience working in multicultural and diverse settings.
• Strong verbal and written English communication skills, including presentation and report writing.

Educational and Experience Requirements

• Ph.D. in computer science, computational science and engineering, or a closely related field is required.
• At least five years of experience with supporting and using large-scale computing platforms and associated subsystems.
• Relevant background in computational science and engineering or closely related areas.
• Experience with parallel computing techniques and storage systems.
• Research experience in areas such as performance modeling (simulation, analytical, or tuning HPC codes), I/O, data management, data compression.
• Familiarity with emerging architectures, including heterogeneous computing and memory systems.
• Proficiency with node-level programming environments such as CUDA, OpenCL, OpenACC/OpenMP compiler directives.
• Experience with distributed system programming models like MPI and one-sided asynchronous programming models.
• Desirable experience includes working on large-scale computing platforms such as those found on the Top500 supercomputing list.