HPC Computational Scientist

Position Overview

We are looking for an experienced HPC Computational Scientist to join our team. This role involves expert-level support for compiling, executing, debugging, and optimizing in-house developed applications on high-performance computing platforms such as the Shaheen III CPU and GPU resources. The position requires offering extensive assistance to users of laboratory HPC systems and associated software.

Key Responsibilities

• Support and enable research activities on King Abdullah University HPC systems across computational science, engineering, big data analysis, artificial intelligence, and machine learning fields.
• Provide specialized knowledge in HPC application installation, library management, porting, performance tuning, and optimization for CPU and GPU architectures.
• Create, update, and maintain comprehensive training materials, user guides, and internal documentation.
• Develop HPC software tools and applications to facilitate research on KSL HPC clusters and the supercomputer.
• Collaborate closely with faculty, researchers, and industry partners to achieve research goals through joint projects.
• Offer prompt user support through multiple communication channels including phone, email, walk-ins, and help desk tickets while maintaining high standards of customer service.
• Conduct installation, tuning, and porting of high-performance applications, tools, and data analysis software.
• Stay current with scientific and technological advances through collaboration, professional development, training, and attendance at conferences.
• Support benchmarking activities to inform future lab procurements and prepare documentation related to system tests and software installations.
• Deliver individual and group training sessions on relevant topics.
• Develop parallel application libraries, software application benchmarks, and other tools to support research on HPC clusters.
• Initiate and pursue research projects aligned with lab objectives; seek co-authorship on scientific papers and presentations; participate in scientific outreach and communication.

Required Skills and Competencies

• Proficiency in supporting and utilizing computational science, engineering, data analysis, and AI/ML applications on various HPC platforms.
• Proven experience working in HPC research environments with collaborative teams.
• Strong programming skills in HPC applications using languages and technologies such as Fortran, C/C++, Python, MPI, OpenMP, CUDA, OpenACC.
• Published research contributions in computational science, engineering, or data analysis journals and conferences.
• Demonstrated capability as a team player with initiative and responsiveness.
• Excellent analytical thinking, problem-solving abilities, and decision-making skills.
• Creativity and innovation in work approaches and solutions.
• Understanding of organizational structures and strategic global perspectives.
• Ability to deliver top-quality results within deadlines.
• Strong planning and organizational skills.
• Comprehensive knowledge of common concepts, practices, and procedures in the relevant field.
• Familiarity with project management principles and methodologies.
• Capability to manage multiple simultaneous projects effectively.
• Cultural adaptability and skill in working within diverse, multicultural environments.
• Effective English communication skills, both written and verbal, including report preparation and oral presentations.

Educational and Experience Requirements

• Ph.D. degree in Computer Science, Computational Science and Engineering, or closely related discipline is required.
• At least five years of experience supporting and utilizing large-scale HPC systems and related subsystems.
• Relevant background in computational science and engineering or a closely related field.
• Experience with parallel computing frameworks and storage systems.
• Research experience preferred in areas such as performance modeling, either via simulation, analytical methods, or code tuning.
• Expertise in I/O systems, data management, and data compression.
• Knowledge of emerging computing architectures, including heterogeneous systems and memory technologies.
• Experience with node-level programming environments such as CUDA, OpenCL, OpenACC, and OpenMP compiler directives.
• Familiarity with distributed programming models like MPI and one-sided asynchronous models.
• Exposure to large-scale computing platforms, ideally with experience on top-tier systems.