Senior HPC Engineer

Senior HPC Engineer

Contract | Inside IR35 | £450–£500 per day

We are seeking an experienced Senior HPC Engineer to support and develop enterprise High Performance Computing (HPC) environments used for complex research, engineering and computational workloads.

This is a hands-on infrastructure engineering role, focused on maintaining and optimising Linux-based HPC platforms, workload scheduling and GPU-accelerated computing environments.

You will work with advanced computing infrastructure, including Red Hat Enterprise Linux, Slurm and NVIDIA GPU platforms, helping ensure performance, availability and reliability across critical HPC environments.

Key Responsibilities

• Administer, maintain and troubleshoot production HPC clusters and compute infrastructure.
• Manage and support Slurm workload scheduling, queues and resource allocation.
• Install, configure, patch and maintain Red Hat Enterprise Linux (RHEL) systems.
• Deploy, administer and troubleshoot NVIDIA GPU infrastructure, including DGX and/or HGX platforms.
• Install, upgrade and maintain NVIDIA drivers, CUDA toolkits and associated GPU software.
• Monitor cluster performance, capacity, availability and resource utilisation.
• Troubleshoot complex Linux, hardware, storage, networking and application issues.
• Provide technical support to researchers, engineers and users running compute-intensive workloads.
• Work with technical teams and infrastructure suppliers to deliver platform improvements.
• Develop automation, operational procedures and technical documentation.

Essential Skills and Experience

• At least 5 years' experience supporting and administering High Performance Computing environments.
• Strong hands-on administration experience with Red Hat Enterprise Linux (RHEL 7, 8 or 9).
• Production experience administering Slurm Workload Manager.
• Experience managing HPC clusters, compute nodes and workload scheduling infrastructure.
• Practical experience supporting NVIDIA GPU-based computing platforms.
• Hands-on experience with NVIDIA DGX and/or HGX systems.
• Strong knowledge of NVIDIA GPU drivers, CUDA installation, configuration and troubleshooting.
• Experience troubleshooting Linux operating systems, hardware, storage and networking within HPC environments.
• Ability to work directly with engineering teams, researchers and technical stakeholders.

Desirable Skills

• HPC storage technologies such as Lustre or IBM Spectrum Scale (GPFS).
• InfiniBand networking and high-performance interconnects.
• AI/ML and GPU-accelerated computing workloads.
• OpenMPI, MPICH or other parallel computing frameworks.
• Automation and configuration management using Ansible.
• Container technologies such as Docker, Apptainer or Singularity.
• HPC hardware lifecycle management, cluster upgrades and expansion.
• Exposure to cloud-based HPC platforms.
• RHCSA, RHCE or NVIDIA certifications.

Contract Details

• Location: UK
• Working arrangement: Hybrid – 3 days onsite per week
• Contract duration: 12 months
• Contract type: Inside IR35
• Day rate: £450–£500