Senior HPC Engineer

We are looking for a Senior HPC Engineer to join on a 12-month hybrid contract based in Stevenage. The role covers the administration, support and optimisation of enterprise High Performance Computing platforms used for research and engineering workloads, ensuring they are reliable, performant and well utilised, and working closely with researchers, engineers, vendors and technical stakeholders to deliver and maintain RHEL, Slurm and Nvidia GPU-based environments., * Run and troubleshoot production HPC clusters, including Slurm scheduling and RHEL systems.

• Deploy and support Nvidia GPU platforms (DGX/HGX), including drivers, CUDA and GPU software.
• Monitor performance, capacity and availability, and fix hardware, OS, storage, network and application issues.
• Support researchers and engineers running compute-heavy workloads.
• Work with vendors on improvements, and build automation, procedures and documentation.

• 5+ years supporting HPC environments
• Strong RHEL (7/8/9) administration
• Hands-on production Slurm administration
• HPC cluster, compute node and scheduler management
• Nvidia GPU platforms, including DGX and/or HGX, driver installation and upgrades, and strong CUDA knowledge
• Troubleshooting across Linux, hardware, storage and networking
• Strong communication, problem-solving and documentation skills

Desirable skills

• Lustre or GPFS storage, InfiniBand
• AI/ML or GPU workloads, OpenMPI/MPICH
• Ansible, Docker or Apptainer/Singularity
• Hardware lifecycle and cluster expansion, cloud HPC
• RHCSA, RHCE or Nvidia certifications