Key ResponsibilitiesLinux Systems Administration

• Administer, configure, patch, harden and upgrade enterprise Linux server platforms, with particular emphasis on Red Hat Enterprise Linux or comparable distributions.
• Manage core Linux services including identity and access integration, SSH, DNS client configuration, time synchronisation, software repositories, filesystems, logging and scheduled services.
• Automate repeatable administration using shell scripting and configuration-management or orchestration tooling.
• Monitor Linux performance, availability, capacity and security, and resolve complex operating-system and application integration issues.
• Maintain build standards, technical documentation, operational procedures and recovery runbooks.

HPC Platform & Workload Scheduling

• Operate and support HPC clusters spanning management, login, compute and storage components.
• Administer SLURM, including queues and partitions, scheduling policies, job submission, accounting, fair-share, reservations and troubleshooting failed or poorly performing workloads.
• Support NVIDIA Base Command Manager and Azure CycleCloud for cluster provisioning, node lifecycle management, monitoring and integration with SLURM.
• Work with engineering and scientific users to diagnose job, compiler, library, MPI, resource-allocation and performance issues.
• Plan and execute maintenance activities while protecting service availability and active workloads.

Compute, Storage & Infrastructure Integration

• Administer physical and virtual server infrastructure and support hardware lifecycle, firmware and operating-system maintenance.
• Support Cisco compute infrastructure and its integration with Linux and HPC management services.
• Operate and support NetApp file and data services used by Linux and HPC platforms, including provisioning, permissions, capacity, performance and availability.
• Apply a working understanding of high-speed networking, IP addressing, routing, DNS, NFS, network dependencies and storage connectivity to end-to-end troubleshooting.

Key ResponsibilitiesLinux Systems Administration

• Administer, configure, patch, harden and upgrade enterprise Linux server platforms, with particular emphasis on Red Hat Enterprise Linux or comparable distributions.
• Manage core Linux services including identity and access integration, SSH, DNS client configuration, time synchronisation, software repositories, filesystems, logging and scheduled services.
• Automate repeatable administration using shell scripting and configuration-management or orchestration tooling.
• Monitor Linux performance, availability, capacity and security, and resolve complex operating-system and application integration issues.
• Maintain build standards, technical documentation, operational procedures and recovery runbooks.

HPC Platform & Workload Scheduling

• Operate and support HPC clusters spanning management, login, compute and storage components.
• Administer SLURM, including queues and partitions, scheduling policies, job submission, accounting, fair-share, reservations and troubleshooting failed or poorly performing workloads.
• Support NVIDIA Base Command Manager and Azure CycleCloud for cluster provisioning, node lifecycle management, monitoring and integration with SLURM.
• Work with engineering and scientific users to diagnose job, compiler, library, MPI, resource-allocation and performance issues.
• Plan and execute maintenance activities while protecting service availability and active workloads.

Compute, Storage & Infrastructure Integration

• Administer physical and virtual server infrastructure and support hardware lifecycle, firmware and operating-system maintenance.
• Support Cisco compute infrastructure and its integration with Linux and HPC management services.
• Operate and support NetApp file and data services used by Linux and HPC platforms, including provisioning, permissions, capacity, performance and availability.
• Apply a working understanding of high-speed networking, IP addressing, routing, DNS, NFS, network dependencies and storage connectivity to end-to-end troubleshooting.