HPC Engineer

Mercedes AMG High Performance Powertrains; Brixworth; On-site; GBP 60,000 - 90,000; Full time

Job summary

Mercedes AMG High Performance Powertrains is seeking an experienced HPC systems administrator in the United Kingdom to own the reliability and performance of our HPC platforms used for simulation and engineering workloads.

You will administer Linux-based clusters, troubleshoot across hardware, OS, network, storage and user workflows, and implement automation using Bash, Python, PowerShell and Ansible. The role focuses on capacity, performance and service improvement.

Qualifications

• Experience administering Linux-based HPC clusters and shared services.
• Ability to troubleshoot hardware, OS, network, storage and user workflows.
• Experience with capacity planning and performance tuning.
• Automation using Bash, Python, PowerShell, Ansible or equivalent.
• Strong communication and collaboration across teams.

Responsibilities

• Own reliability, availability and performance of HPC platforms.
• Improve compute, storage, networking and scheduling services.
• Provide technical escalation for HPC incidents and bottlenecks.
• Automate operational tasks with scripting and automation tools.
• Translate user requirements into practical service improvements.

Skills

HPC administration

System troubleshooting

Capacity planning

Automation scripting

Collaborative communication

Education

Relevant degree

Tools

Slurm

PBS

LSF

Ansible

Python

PowerShell

Job description

• Own the reliability, availability and performance of HPC platforms supporting simulation, analysis and engineering workloads
• Improve compute, storage, networking and scheduling services to enable efficient, scalable workload delivery
• Provide technical escalation for HPC incidents, capacity issues, performance bottlenecks and complex user problems
• Administering Linux-based HPC clusters, including compute nodes, schedulers and shared platform services
• Troubleshooting issues across hardware, OS, network, storage, applications and user workflows
• Managing capacity, performance and availability for engineering and simulation workloads
• Automating operational tasks using Bash, Python, PowerShell, Ansible or equivalent tools
• Translating technical user requirements into practical service improvements

Purpose of the role is to…

• Own the reliability, availability and performance of HPC platforms supporting simulation, analysis and engineering workloads
• Improve compute, storage, networking and scheduling services to enable efficient, scalable workload delivery
• Provide technical escalation for HPC incidents, capacity issues, performance bottlenecks and complex user problems

THEREFORE WE NEED YOU TO…

• Administering Linux-based HPC clusters, including compute nodes, schedulers and shared platform services
• Troubleshooting issues across hardware, OS, network, storage, applications and user workflows
• Managing capacity, performance and availability for engineering and simulation workloads
• Automating operational tasks using Bash, Python, PowerShell, Ansible or equivalent tools
• Translating technical user requirements into practical service improvements

Be skilled at…

• Administering Linux-based HPC clusters, including compute nodes, schedulers and shared platform services
• Troubleshooting issues across hardware, OS, network, storage, applications and user workflows
• Managing capacity, performance and availability for engineering and simulation workloads
• Automating operational tasks using Bash, Python, PowerShell, Ansible or equivalent tools
• Translating technical user requirements into practical service improvements

Have Experience Of…

• Supporting Linux-based HPC, scientific computing, simulation or high-throughput compute environments
• Diagnosing workload, queue, licence, performance, data movement and application issues
• Operating at a senior technical level in an enterprise or engineering-led environment
• Delivering maintenance, upgrades, patching and change activity with minimal service impact
• Working with suppliers and internal teams to resolve platform issues and improve service maturity

Demonstrate knowledge of…

• HPC architecture, parallel workloads, scheduling, queues and resource allocation
• Linux administration, scripting, patching and secure configuration
• Schedulers such as Slurm, PBS, LSF or equivalent
• Scale-out storage, file systems, backup, archive and data lifecycle management
• Networking, interconnects, latency, bandwidth and data locality considerations
• Monitoring, performance tuning, benchmarking and capacity forecasting
• Security, vulnerability management, access control and compliance for shared platforms
• Desirable: motorsport, automotive, CFD, simulation or data science experience

Hold These Qualifications…

• Relevant degree, apprenticeship, professional qualification or equivalent technical experience
• Relevant technical certifications, or equivalent experience, in Linux, HPC, storage, networking, automation or ITIL

Be…

• Analytical, curious and comfortable solving complex technical problems
• Proactive in improving resilience, reducing risk and removing operational friction
• Structured, communicative and effective across hands-on delivery and change control
• Collaborative, customer-focused and willing to share knowledge

Success in this role will be if you… (deliverables)

• Maintain stable, secure and performant HPC services for critical engineering workloads
• Improve compute and storage utilisation through effective monitoring, queue management and capacity planning
• Resolve incidents quickly and reduce repeat issues through automation, documentation and service improvement
• Deliver upgrades, maintenance and project work safely with clear communication and change control
• Improve simulation throughput, data availability and user productivity
• Define and guide strategic direction on HPC related topics

Additional Information…

• The role combines operational support and project delivery, including planned maintenance, capacity improvement, lifecycle management and occasional out-of-hours activity