HPC Engineer

Osmii; Northampton; On-site; GBP 65,000 - 90,000; Full time

Job summary

Osmii in the United Kingdom seeks an experienced HPC Engineer to own and optimise the reliability, availability, and performance of Linux-based HPC clusters and shared services. You will support engineering workloads and shape the long-term HPC direction.

Responsibilities include incident leadership, workload optimization across compute/storage/networking, and proactive capacity management to sustain high-throughput simulations.

Qualifications

• Experience with Linux-based HPC, scientific computing, or high-throughput compute environments.
• Hands-on scripting and automation using Bash, Python, PowerShell or Ansible.
• Understanding of performance tuning and capacity planning for HPC platforms.
• Familiarity with CFD/FEA or data science workloads is a plus.
• Knowledge of security, access controls, and compliance in multi-tenant HPC.
• Strong problem-solving, analytical, and cross-team communication skills.
• Experience with workload managers and cluster schedulers.

Responsibilities

• Platform Ownership: maintain stability, security, and performance of Linux-based HPC clusters.
• Workload & Service Optimization: improve compute, storage, networking, and scheduling for throughput.
• Incident & Problem Resolution: act as escalation lead for complex incidents and bottlenecks.
• Automation & Efficiency: automate recurring tasks and deployments using scripting and tooling.
• Lifecycle & Capacity Management: monitor, tune, benchmark, and forecast capacity needs.
• Maintenance & Change Delivery: plan OS patches, upgrades, and hardware refreshes safely.
• Strategic Input: shape HPC architecture roadmap with internal teams and vendors.

Skills

Scripting & automation

Linux HPC support

Performance tuning

CFD/FEA workloads

Security & compliance

Collaboration & communication

Tools

Slurm

PBS

LSF

Job description

We are seeking an experienced and analytical HPC Engineer to take ownership of the reliability, availability, and performance of our High-Performance Computing (HPC) platforms. In this role, you will support critical engineering, simulation, and analytical workloads, ensuring our compute, storage, networking, and scheduling environments are optimised to deliver scalable, high-throughput results.

You will act as the technical escalation point for complex platform incidents, performance bottlenecks, and capacity challenges, while helping shape the long-term technical direction of our

HPC infrastructure.

Key Responsibilities

• Platform Ownership: Maintain the stability, security, and performance of Linux-based HPC clusters, compute nodes, and shared platform services.
• Workload & Service Optimization: Enhance compute, storage, networking, and scheduling services to maximize simulation throughput and resource utilization.
• Incident & Problem Resolution: Serve as the technical escalation lead for complex incidents, hardware/OS faults, network/storage latency issues, and queue bottlenecks.
• Automation & Efficiency: Automate repetitive operational tasks and deployments using Bash, Python, PowerShell, Ansible, or equivalent tooling.
• Lifecycle & Capacity Management: Drive proactive monitoring, performance tuning, benchmarking, and capacity forecasting to stay ahead of engineering demand.
• Maintenance & Change Delivery: Plan and deliver maintenance, OS patching, system upgrades, and hardware refreshes safely with minimal service disruption.
• Strategic Input: Help define and guide the strategic roadmap for HPC architectures, collaborating closely with internal engineering teams and external technology vendors.

What We Are Looking For

Core Technical Skills & Experience:

• Proven track record supporting Linux-based HPC, scientific computing, high-throughput compute, or simulation environments.
• Deep knowledge of workload managers and schedulers (e.g., Slurm, PBS, LSF, or equivalent).
• Solid understanding of scale-out storage, parallel file systems, data lifecycle management, archive, and backup strategies.
• Practical knowledge of high-performance networking, interconnects, low-latency architectures, bandwidth considerations, and data locality.
• Hands-on scripting and automation capability (Python, Bash, PowerShell, Ansible).
• Demonstrated experience troubleshooting across the full stack—from bare-metal hardware and operating systems to application licensing and user workflows.
• Strong background in platform security, vulnerability management, access controls, and compliance for multi-tenant, shared computing environments.

Mindset & Approach:

• Methodical problem-solver who remains calm and structured when troubleshooting high-priority issues.
• Proactive mindset focused on reducing technical debt, preventing repeat incidents, and optimizing performance.
• Collaborative communicator who can translate complex technical requirements into reliable production services.
• Direct experience supporting Computational Fluid Dynamics (CFD), finite element analysis (FEA), motorsport/automotive engineering, or data science workloads.
• Relevant technical certifications in Linux administration, HPC, networking, storage, automation, or ITIL frameworks.