HPC System Admin

What the role does

This is the core Linux/HPC infrastructure operations role.

The role is responsible for keeping the compute and operating-system environment healthy.

Day-to-day scope

·       Operate and support compute nodes.

·       Support login nodes.

·       Manage OS lifecycle.

·       Perform configuration management.

·       Maintain HCI/virtualisation systems.

·       Troubleshoot OS/system problems.

·       Monitor system health.

·       Investigate hardware/OS-related incidents.

·       Support planned maintenance.

·       Perform approved changes.

·       Escalate hardware/OEM issues where necessary.

The baseline specifically describes this role around OS lifecycle, configuration management, login/compute/HCI operations and support.

Maintenance scope

·       OS patching.

·       System updates.

·       Configuration changes.

·       Validation after maintenance.

·       Troubleshooting failed changes.

·       Maintaining system configuration records.

·       Supporting incident recovery.

Incident scope

Examples of issues this person would be expected to deal with include:

·       Login node unavailable.

·       Compute node unavailable.

·       OS failure.

·       System configuration issue.

·       Node performance issue.

·       HCI/virtualisation issue.

·       Post-patch problem.

Key skills

·       Linux administration

·       Red Hat Linux

·       System troubleshooting

·       Linux system lifecycle management

·       Configuration management

·       Shell scripting

·       Compute-node administration

·       Login-node administration

·       HCI/virtualisation

·       Monitoring

·       Incident troubleshooting

·       Change management

Minimum requirements

·       ≥3 years relevant experience

·       ITIL Foundation or equivalent/higher

·       Red Hat Certified System Administrator (RHCSA) or equivalent/higher