High Performance Computing Analyst required to help ensure HPC facilities meet availability, performance and usability requirements. The successful candidate will have a university degree and experience of
1. Parallel processing computer systems including large-scale Linux clusters.
2. Unix or Linux systems administration, Unix shells, Python or Perl and configuration management.
3. C, Fortran, MPI and/or OpenMP programming.
4. High-Performance Computing facility running at least a hundred thousand jobs a day.
Main duties and key responsibilities
5. Facilitate efficient use of HPC facilities support groups, developers and end users with assistance, tools and training by
6. Resolving user and operational problems operating systems and HPC software stack.
7. Configuring, testing, tuning and go live of new HPC hardware.
8. Install, maintain, configure and tune the operating system, high-performance interconnects, parallel filesystems, batch scheduling systems, standard utilities, user environment and locally developed tools on the HPC facilities.
9. Continuously improve resiliency
10. Provide on-site 24x7 monitoring staff with information, procedures and training that they need.
11. Implement security for HPC systems.