Senior Storage Systems Administrator

A new and exciting opportunity has arisen for an enthusiastic and highly motivated Senior Storage SysAdmin to join the University's Advanced Computing Research Centre (ACRC), one of the UK's leading High Performance Computing (HPC) and Research Data Storage (RDS) providers.  The University's latest HPC cluster contains more than 15,000 compute cores and provides over 800 TFlops.  This computing power is coupled to a multi-petabyte, highly-resilient and highly-available storage facility serving thousands of users.

The role holder will be at the forefront of bringing innovative and highly performant storage solutions to a large and vibrant community of researchers.  The ideal candidate for this role will combine an appetite for new technology and innovation with system development and planning together with problem solving, strong user support ethos and excellent communication skills.  The role holder will be part of a team of Systems Administrators, Data Specialists and Research Software Engineers who support the administration and operation of high performance parallel file systems and the development of innovative data sharing facilities.

The role holder will support a wide variety of researchers and workflows and will have the opportunity to engage with many cutting-edge storage technologies.  The role holder will be part of the team implementing the strategy to support the growing research data storage requirements of the University and of the HPC facility.  They will manage the day to day operation of the infrastructure underpinning the RDS service; this will include software installation and maintenance, using modern configuration tools such as Ansible, version control using Git, monitoring of workloads using tools such as Icinga, InfluxDB and Grafana, logging of estate, e.g. using Elasticsearch, Logstash and Kibana data movement and storage, and storage related network operations both internal and external to the RDS Facility and ACRC HPC systems.

The RDS uses IBM's Spectrum Scale parallel file system backed by several petabytes of disk and SSD storage.  An innovative Hierarchical Storage Management system couples this to tens of petabytes of tape storage.  The backend storage libraries and arrays are connected by a Fibre Channel SAN to highly available cluster of servers providing network attached storage to over 3,000 users.  The RDS is far from static and we are currently investigating the use of new SSD-based caching technologies along with bespoke data migration and placement policies. Looking ahead, we are planning for the next 20 years of data storage, with the role holder playing a significant part in the development of the next generation of our storage facility.

This is an open-ended position.

Closing date - Monday 8th October 2018. Interviews will be held on Friday 19 October.

For informal enquiries please contact either Simon Burbidge (simon.burbidge@bristol.ac.uk) or Caroline Gardiner (Caroline.Gardiner@bristol.ac.uk).

We appreciate and value difference, seeking to attract, develop and retain a diverse mix of talented people that will contribute to the overall success of Bristol and help maintain our position as one of the world's leading universities.