System Administrator: HPC & Large-Scale Storage

Commonwealth Scientific and Industrial Research Organisation; Western Australia; On-site; AUD 95,000 - 140,000; Full time

Job summary

Commonwealth Scientific and Industrial Research Organisation (CSIRO) invites applications for a System Administrator role at Pawsey Supercomputing Research Centre in Kensington, Perth. You will help deliver and maintain large-scale storage platforms powering researchers across Australia, ensuring availability and performance of data services.

You will join a skilled team, contribute to Ceph-based storage, archival systems, and HPC environments, and work across Linux systems, cloud tech, and

Qualifications

• Tertiary or graduate qualification in Science, Computing or Engineering, or equivalent experience.
• Experience in the administration of Linux or Unix systems.
• The ability and willingness to spend time learning not only the specific systems you will be responsible for maintaining, but also the systems connected to those systems, and the tools associated with the main system and those related systems.
• Excellent verbal and written communication skills, and the ability to use these skills to engage effectively with colleagues and clients.
• The ability to work effectively independently and as part of a team under the general guidance of senior technical staff.
• The ability and willingness to contribute novel ideas and approaches in support of providing computing services to researchers or clients.
• Knowledge of programming languages (such as Python) and source code management tools.
• Experience operating Ceph storage infrastructure, other storage technologies (e.g. tape-backed systems such as DMF, TSM, Versity ScoutAM), or OpenStack.
• Experience with Internet technologies such as web servers, database servers and mail servers.
• Exposure to High-Performance Computing environments (e.g. experience with workload schedulers such as Slurm or PBS Pro), high-performance filesystems (Lustre, VAST, Weka) or container orchestration environments.
• Demonstrated success in managing compute and storage systems in a research environment.
• Experience with automation, testing or provisioning technologies such as Ansible, MAAS, xCat, Redhat Satellite, HPE HPCM, goss and Jenkins.
• Exposure to the design and deployment of new services or platforms for use by researchers or clients.

Responsibilities

• Supporting the operation and maintenance of large-scale storage and computing infrastructure.
• Administering Linux-based systems and storage platforms used by Australia's research community.
• Assisting with the operation of object storage, archival storage and associated infrastructure.
• Troubleshooting system issues and improving operational workflows.
• Responding to and resolving support requests within agreed service expectations.
• Developing and maintaining technical documentation and operating procedures.
• Contributing to continuous improvement initiatives and service enhancements.
• Working collaboratively with colleagues, researchers, vendors and stakeholders.
• Supporting the deployment, maintenance and optimisation of research computing services.
• Participating in hands-on infrastructure activities including hardware maintenance and equipment servicing where required.

Skills

Linux administration

Python scripting

Ceph storage

OpenStack

Automation tools (Ansible, MAAS)

Education

Tertiary or graduate qualification in Science, Computing or Engineering

Tools

Ceph storage infrastructure

DMF

TSM

Versity ScoutAM

OpenStack

Lustre

Slurm

PBS Pro

Git

Ansible

Job description

Commonwealth Scientific and Industrial Research Organisation (CSIRO) invites applications for a System Administrator role at Pawsey Supercomputing Research Centre in Kensington, Perth. You will help deliver and maintain large-scale storage platforms powering researchers across Australia, ensuring availability and performance of data services.

You will join a skilled team, contribute to Ceph-based storage, archival systems, and HPC environments, and work across Linux systems, cloud tech, and