Senior HPC Systems Specialist

Position Number: 001982

Department: Office of OneIT (Adm)

Employment Type: Permanent - Full-time

Months Per Year: 12

Essential Duties and Responsibilities:

This Senior HPC Systems Specialist serves as a key team member reporting to the Director of University Research Computing. This position performs critical systems management and other operational duties, with responsibilities and objectives delegated by the Director. This position contributes to shaping the strategic direction of University Research Computing. At times, this position may provide leadership or supervision of the technical work of other staff members.

This position is responsible for supporting the ongoing operation of the Research Computing facilities, including systems management and maintenance, developing and deploying upgraded capability, and interacting with and supporting users. The position is also responsible for supporting technical design and strategy development. The position also includes responsibility for directing the technical work of other members of staff.

Minimum Experience / Education:

• Bachelor’s degree and 4+ years of progressively responsible experience designing, provisioning, administering, and supporting production HPC systems and clusters; or

• An equivalent combination of education and relevant work experience.

Preferred Education Skills and Experience:

• Experience installing, maintaining, and optimizing HPC scientific applications, libraries, and toolchains ( MPI , OpenMP, CUDA , compilers, numerical libraries).

• Proficiency with HPC software management tools such as EasyBuild and Spack, and environment module systems such as Lmod.

• Experience supporting researchers in higher education or research environments by troubleshooting job failures, optimizing workflows, debugging application issues, and providing technical guidance.

• Experience with HPC monitoring, logging, and accounting tools, including Grafana, Prometheus, Slurm accounting, Elastic Stack, or similar monitoring platforms.

• Experience supporting GPU computing environments, including NVIDIA drivers, CUDA , GPU scheduling, monitoring, and performance optimization; familiarity with AMD ROCm is desirable.

• Experience with container technologies in HPC environments, including Apptainer/Singularity, and supporting reproducible containerized research workflows.