Senior HPC Engineer

Gazelle Global; Stevenage; Hybrid; GBP 60,000 - 90,000; Full time

Job summary

Gazelle Global seeks a Senior HPC Engineer to join a major scientific computing environment on a 12-month contract in Stevenage. The role is hands-on, focusing on maintaining, securing and optimising Linux-based HPC infrastructure and collaborating with researchers to run complex workloads.

You’ll manage HPC clusters and workstations, ensure reliability and security, and support scientific applications. The position is hybrid with three days on-site in Stevenage.

Qualifications

• Hands-on administration of RHEL 7/8/9 in HPC environments.

Responsibilities

• Maintain Linux-based HPC infrastructure, ensuring security and performance.
• Support scientific applications and high-computation workloads.
• Collaborate with researchers and technical teams on HPC projects.
• Configure and manage Slurm workloads and HPC clusters.
• Troubleshoot hardware, OS, and scheduler issues.
• Work in a hybrid model with three onsite days in Stevenage.

Skills

HPC cluster administration

Slurm workload management

MPI workloads

Linux administration (RHEL 7/8/9)

GPU computing / CUDA

InfiniBand / high-speed Ethernet

Troubleshooting hardware, OS, sched

Security hardening of HPC

Tools

Ansible

ServiceNow ITSM

CUDA development tools

InfiniBand networking

Job description

We're looking for a Senior HPC Engineer to join a major scientific computing environment on a 12-month contract in Stevenage. This is a hands-on role focused on maintaining, securing and optimising Linux-based HPC infrastructure, with the opportunity to work closely with research scientists and technical teams.

You’ll be responsible for keeping HPC clusters and high-end workstations reliable, secure and performing efficiently, while supporting scientific applications and complex computational workloads.

Key Skills:

• Strong hands-on administration of RHEL 7, 8 and 9
• HPC cluster administration and troubleshooting
• Slurm deployment, configuration and workload management
• Scientific applications within Linux HPC environments
• MPI libraries and computational workloads
• Hardware, OS and scheduler troubleshooting
• ServiceNow or equivalent ITSM experience
• GPU computing and CUDA knowledge
• Ansible or similar automation tools
• HPC networking, including InfiniBand/high-speed Ethernet

The role is hybrid, with 3 days per week onsite in Stevenage.