HPC Systems Engineer

Salary: £45,000 - £50,000 per annum

Industry: Automotive

Job Type: Permanent

Location: South East

Reference: 28533-jh

Expiration date: 06 March 2018

We have an exciting opportunity for an experienced High Performance Computing (HPC) Engineer to join the HPC team supporting the engineering simulation groups within our innovative motorsport technology client based in the Bedfordshire area on a permanent staff basis.

You should be enthusiastic about all aspects of HPC and modern HPC technologies, tools and methodologies including DevOps.
The role will be to implement and maintain High Performance Computing infrastructure for Computational Fluid Dynamics (CFD), structural analysis (FEA) and vehicle dynamics simulations.
Support HPC infrastructure projects from requirements definition through to deployment.
Provide operational support of HPC infrastructure where to provide a reliable, high performance, scalable cost effective and secure environment.

Principal Accountabilities:

  • Support projects to specify and implement HPC infrastructure including compute, storage, networking, operating systems, management tools and application software. Work closely with engineering users to capture requirements and to develop optimal configurations. Also work closely with vendors to leverage their expertise and solutions.
  • To execute proof of concepts (POCs) and to implement new technology.
  • Participate in the administration of HPC infrastructure to ensure systems are effective, reliable, highly performant and secure. Work with internal IT staff to optimize procedures and resource allocation. Manage external service providers to ensure appropriate SLAs and procedures are in place.
  • Provide technical oversight, training and consultation to engineers that use HPC solutions. Work with internal IT staff to optimize procedures and resource allocation.
  • Participate in the IT Architecture Review board to review infrastructure concepts for new projects.

Essential Skills & Competencies:

  • Stay up to date with new technology that has the potential to improve business performance.
  • Thrives in a dynamic, fast paced and highly technical environment. Strong communication and time management skills. Independent and self-motivated. 
  • Linux expertise.
  • Network expertise including Ethernet and possibly InfiniBand
  • Storage expertise including HPC hardware, cloud solutions, Spectrum Scale and Protect
  • HPC hardware expertise including clusters, pre/post processing servers and clients
  • Ability to effectively understand infrastructure requirements for new applications.
  • Experience in High Performance Scientific or Technical Computing applications including Computational Fluid Dynamics (Fluent) and Structural Analysis (Abaqus).

Desired Skills & Competencies:

  • Knowledge of IBM Spectrum software defined infrastructure solutions (Scale, Protect, LSF, Symphony, etc.) or other similar job scheduling and/or resource managers.
  • Cluster provisioning software including XCAT or similar.
  • High performance networking including Mellanox InfiniBand and/or Intel OmniPath including Message Passing libraries (MPI).
  • Shared File Systems including NFS and parallel files systems (GPFS or Lustre).
  • Container technologies, including Docker or Singularity.
  • “Agile” methodologies, DevOps and associated toolchains beneficial although not essential.
  • Scripting and programming languages including Bash, Python, C, C++ and Perl.

You will be expected to be flexible in terms of working hours including weekend support on a shared rota basis to support the dynamic nature of the business.