Job Title: HPC Systems Engineer - Enterprise Linux & Cluster Infrastructure
Below covers everything you need to know about what this opportunity entails, as well as what is expected from applicants.
Location: Hybrid to Remote - Swansea (mostly remote & expenses for all site travel)
Day Rate: £465 per day - payable to Limited Company / Outside IR35
Duration: 4 months initially
Pay Frequency: Weekly
Start Date: ASAP
Overview
We are seeking an experienced HPC Systems Engineer to deploy, configure, optimise and support high-performance computing (HPC) environments. This includes large-scale Linux clusters, GPU-accelerated systems, and associated storage, networking, and authentication infrastructure.
Although this role is hybrid, it's expected to be largely remote / WFH.
Responsibilities
* Deploy, configure, optimise and support enterprise Linux across HPC clusters
* Automate provisioning and manage configuration at scale (PXE, Kickstart, Ansible/Puppet)
* Install, configure, and optimise HPC schedulers (e.g. Slurm) and MPI environments
* Deploy and manage GPU (NVIDIA/CUDA) and high-performance storage solutions
* Monitor, benchmark, and tune system performance across compute, network, and storage
* Implement authentication, security controls, and system hardening for multi-user environments
* Support HPC software stacks, toolchains, and container runtimes (Spack, EasyBuild, Apptainer)
* Maintain documentation and support user access/workflows xsngvjr
Requirements
* Strong Linux administration in HPC or large-scale environments
* Experience with automation and cluster provisioning
* Knowledge of Slurm, MPI, and parallel computing
* Experience with GPU/CUDA environments
* Understanding of system performance tuning
* Familiarity with identity management and security best practices
* Previous experience operating as an HPC Systems Engineer