Role: Sr. HPC Administrator

Desired Experience Range: 7 - 12 yrs

Notice Period: Immediate to 60 Days only

Location of Requirement: Bangalore

JOB DESCRIPTION

• Strong experience in providing support for Linux HPC clusters.
• Strong working knowledge on Following:
• IBM Platform LSF 9 and 10 administration.
• Redhat Enterprise Linux Administration.
• Lustre Parallel File system.
• Mellanox Infiniband Connectivity.
• Cluster Manager Administration (HPCM or xCAT)
• SSSD & NIS Authentication mechanisms.
• Bash & Python scripting.
• Ansible playbooks.
• Experience of Abaqus, and CFD application (Fluent and StarCCM..etc.,)
• Strong knowledge of application installations and version management on shared file systems.
• IT infrastructure Technical Operation Management under ITIL framework
• Security compliance and remediation management.

Intermediate Level

• DevOps, ITIL, Agile, Safe (certifications are desirable)

Responsibilities

• Installation, configuration, troubleshooting and administration of Linux HPC clusters (compute,

storage, and network) and applications in support of CAE environments.

• Monitor and analyze LSF job queues and resource utilization to optimize workload management.
• Troubleshoot and resolve any issues with LSF and its components, including master servers, compute

nodes, and resource managers.

• Collaborate with users to understand their HPC requirements and design LSF job workflows to meet

their needs.

• Develop and maintain LSF documentation, including standard operating procedures, installation

guides, and troubleshooting procedures.

• Develop and maintain LSF scripts for automation and task scheduling.
• Diagnose and troubleshoot complex RHEL OS, application and HPC cluster technical problems.
• Interact with hardware and software vendors for external support.
• Develop and maintain technical solution documents (TSD) and standard operating procedures(SOP).
• Keep all HPC infrastructure systems/servers/devices up to date and working condition to enhance

business continuity.

• Design and implement HPC network topology, including Mellanox connectivity.
• Create and maintain HPC capacity planning and periodical cluster utilization reports.
• Troubleshoot Abaqus, StarCCM+ and Fluent applications, and resolve any issues in a timely manner.
• Develop and maintain scripts for automation and task scheduling using Python and Bash scripting.