Systems and HPC Administrator

The Yusuf Hamied Department of Chemistry wishes to appoint a Systems and HPC Administrator to a strategically significant new role within the Department's friendly IT team. The team enjoys a reputation for delivering highly available services that are responsive to the needs of the Department. This is achieved through the implementation of effective processes underpinned by consistent configuration of the IT infrastructure. The IT team also pursues simplification of the infrastructure and the decommissioning of obsolete systems in order to minimise technical debt.

The IT team works in an integrated fashion and takes collective responsibility for the delivery of IT services. However, this role requires a senior technical leader capable of working at a strategic level to create and deliver department-wide change. The successful applicant will split their time roughly equally between supporting research groups using specialist High Performance Computing (HPC) and maintaining core IT systems used by all members of the department.

The role holder shall:

• Provide expert guidance and shape policy regarding the full lifecycle of HPC hardware. This includes specifying complex architectures, overseeing procurement, and managing the sustainable decommissioning of high-value assets.
• Configure and maintain complex software stacks tailored to specific scientific needs, ensuring researchers can utilise specialised hardware effectively.
• Manage and develop core IT services (such as network management, storage, VM hosting, and web services) to ensure the resilience and security of the infrastructure that underpins the Department's world-leading research.
• Collaborate on the Department's IT roadmap, identifying and delivering projects that enhance infrastructure and evolve support services alongside the changing needs of research groups.

The IT team uses a variety of technologies. Our IT infrastructure is predominantly Linux-based, and the HPC environment utilises specialist interconnects (e.g., InfiniBand), workload managers (e.g., Slurm) and software stacks. While the applicant is not expected to know all the technologies used, they should have a strong foundation in Linux administration and a willingness to rapidly learn specialist HPC tools and automation frameworks (e.g., Ansible).

Key skills for the role holder include:

• An ability to take responsibility and work well with colleagues in the team, specifically collaborating with other senior members on infrastructure and HPC strategy.
• Strong technical skills, including the ability to automate routine tasks and to identify complex technical faults at source.
• A proactive, problem-solving attitude to assist scientific colleagues with intricate and difficult technical challenges.
• Good communication and interpersonal skills to confidently interact with students, researchers, professional services and senior academic staff.

The successful candidate will have a degree level qualification or equivalent experience, ideally in a numerate science, but other candidates with a strong track record in HPC and/or systems administration will be seriously considered.

To apply online for this vacancy and to view further information about the role, please click the ‘Apply’ button above.

For informal queries please contact the IT Manager, Frank Lee (rl201@cam.ac.uk).

Please quote reference MA48318 on your application and in any correspondence about this vacancy.

The Department holds an Athena SWAN silver award for women in Science, Technology, Engineering, Mathematics, and Medicine.

The University actively supports equality, diversity and inclusion and encourages applications from all sections of society.

The University has a responsibility to ensure that all employees are eligible to live and work in the UK.

Advert information