Job description

Job summary

Imperial College London is a world leading, top ten university and is home to the greatest concentration of high-impact research of any UK university. The Research Computing Service (RCS) provides support for High-Performance Computing, a team of Research Software Engineers, and support for a growing number of research applications that support the research data lifecycle.

Here is an opportunity for a technically skilled professional to support world leading research. As a Research Infrastructure Engineer your role will be key to developing and supporting high-performance computing and associated research data platforms at Imperial both on-premise and in the cloud. You will ensure researchers, whatever their field, have access to the most appropriate equipment and technology for their work.

The role provides opportunities to learn and develop new skills, working as part of a team of research computing specialists, and as part of the broader RCS and Imperial College ICT team.

Research Computing Services HPC estate is a large, heterogeneous system with both proprietary and commodity clusters. It includes high-throughput capacity, high-end capability, GPU compute and large-memory services and is tailored to support the diverse computing needs of the research community.

The evaluation and integration of new technology plays a major part in provisioning research computing systems.  This role provides the opportunity to develop on-premise HPC and evaluate and implement new cloud-based technologies. Together with our team of analysts, you will provide advice to researchers.

Duties and responsibilities

• Be responsible for the installation, configuration, and support of services as required within the central Research Computing Services platform team.


• Work with vendors and ICT’s Technology Office to design, implement and upgrade services using change management and revision control processes to ensure that changes are properly tracked and available for audit when required.


• Analyse and troubleshoot system issues, defining, and resolving complex issues.


• Develop innovative solutions to continuously improve HPC and address shortfalls in provision.


• Maintain a knowledge of technical developments, tools, and ideas in HPC, attending seminars, conferences, technical briefings, and other community events.


• Deliver a high-quality service through a collaborative approach and outstanding analytical skills.


• Take an active part in meetings, representing the College, and facilitating collaboration between partners.


• Assist researchers to utilise the HPC resource, providing subject matter expertise support to the Research Computing Analysts.

Essential requirements

• A degree in a scientific or technical discipline or relevant experience


• Experience in designing and implementing services


• Experience in evaluating hardware and software technologies and selecting those that fit the requirements


• Experience of working in a customer orientated support service or a research/technology environment, with a positive attitude to delivery.


• Practical experience of using Linux and HPC clustered computing software stacks such as provisioning, monitoring, parallel command execution and scheduling/queuing solutions


• Knowledge of HPC environments, parallel programming methodologies and service components.


• Knowledge of operational software in an HPC environment, as used for monitoring, parallel command execution and job scheduling such as PBSPro, Slurm and Moab.


• Knowledge and experience of debugging applications.

Further information

Full description of this role can be found in the Job Description.

Please note this is a re-advertisement; previous applicants need not apply.

This is a full time and open ended role, and you will based in the South Kensington Campus.

Should you require any further details on the role please contact Andrew Richards (a.j.richards@imperial.ac.uk) or Dugan Witherick (d.witherick@imperial.ac.uk)

The College is currently trialling a Work Location Framework until early 2023.  Hybrid working may be considered for this role and the role holder may be expected to work 60% or more of their time onsite, with 40% the minimum time spent onsite.  The opportunity for hybrid working will be discussed at interview.

Documents

• JD - Senior Research Infrastructure Engineer.pdf