HPC Senior Systems Administrator

Position summary

Responsibilities

• Provide user support by telephone, walk-in, email, and ticketing system.
• Install, configure, and manage compute nodes, high-performance storage, InfiniBand and Ethernet, and configuration management tools.
• Deploy and manage cluster management software, monitoring tools, and services.
• Administer Slurm, QoS policies, accounts, accounting, and automation scripts.
• Develop Bash and Python automation and manage Singularity/Apptainer and Docker container environments.
• Benchmark CPU, memory, network, and storage; identify tuning opportunities across hardware, drivers, and applications.
• Enforce security practices, including node hardening, kernel patching, and compliance.
• Manage parallel file systems, performance tuning, and capacity planning.
• Support research workloads and develop tools for cluster systems and subsystems.
• Lead proof-of-concept projects and technology evaluations; research best practices and advocate system improvements.
• Coordinate with vendors and service providers to resolve issues.
• Maintain user documentation, SOPs, and training materials; contribute to benchmarking that informs future hardware procurement.

Competencies

• Expertise supporting computational science, engineering, data analysis, and AI applications and libraries in HPC environments.
• Strong Linux administration in large-scale HPC environments; RHEL, Rocky Linux, or CentOS.
• HPC applications and programming models include Fortran, C/C++, Python, MPI, OpenMP, CUDA, and OpenACC.
• Experience with parallel file systems, job schedulers, InfiniBand/Ethernet networks, monitoring systems, and configuration management such as Ansible or Puppet.
• Knowledge of project management; analytical, problem-solving, decision-making, collaborative, and communication skills.
• English verbal and written communication, including technical reports and presentations; ability to work across concurrent projects and multicultural teams.

Qualifications and experience

• Bachelor’s or master’s degree in computer science, engineering, Information Systems, or equivalent.
• At least 5 years supporting large-scale computing platforms and related subsystems.
• Experience troubleshooting complex hardware and documenting root-cause analysis.
• Experience managing parallel storage systems such as Lustre, GPFS, Weka, Vast, or similar.
• Experience benchmarking CPU, memory, InfiniBand, and storage.