HPC Linux & Lustre File System Support Engineer

Roles And Responsibilities

Required technical skills

• Hands-on administration and troubleshooting of Lustre parallel le systems.

• Strong Linux administration: RHEL, Rocky, AlmaLinux, SLES, or Ubuntu.

• Lustre components: MDS/MDT, OSS/OST, clients, LNet, quotas, recovery, performance analysis, monitoring

• HPC cluster stacks/provisioning: OpenHPC, xCAT, Bright, Warewulf, PXE, Cobbler, or equivalent

• Schedulers: Slurm, PBS Pro, LSF, or equivalent

• Networking: InniBand, RDMA, Ethernet, Mellanox/NVIDIA, LNet troubleshooting

• Storage: ZFS, RAID, enterprise storage, capacity planning, backup/recovery

• Bash/Python scripting and Ansible automation

• SOPs, runbooks, change plans, incident reports, and RCA writing

• Ability to follow client security controls, change management, and SLA escalation

Preferred

• 3-5 years project experience needed. Project reference needed.
• HA Lustre deployments, upgrades, migrations, recovery
• GPFS / IBM Storage Scale, NetApp, Dell, HPE storage
• Support of AI/ML, CAE/CFD, research, rendering, or simulation workloads
• India-based; Chennai / Bengaluru / Hyderabad / Pune availability . Chennai Location preferred.
• Review supplied architecture/conguration details
• Produce a Lustre/HPC health-check report and risk register
• Recommend monitoring, alerting, backup, and runbook improvements
• Technical walkthrough with SBA Info Solutions
• A support approach for L1 to L3 incidents
• Schedulers: Slurm, PBS Pro, LSF, or equivalent
• Networking: InniBand, RDMA, Ethernet, Mellanox/NVIDIA, LNet troubleshooting
• Storage: ZFS, RAID, enterprise storage, capacity planning, backup/recovery
• Bash/Python scripting and Ansible automation
• SOPs, runbooks, change plans, incident reports, and RCA writing
• Ability to follow client security controls, change management, and SLA escalation

Preferred

• HA Lustre deployments, upgrades, migrations, recovery
• GPFS / IBM Storage Scale, NetApp, Dell, HPE storage
• Support of AI/ML, CAE/CFD, research, rendering, or simulation workloads
• India-based; Chennai / Bengaluru / Hyderabad / Pune availability

Chennai Location preferred.

• Review supplied architecture/conguration details
• Produce a Lustre/HPC health-check report and risk register
• Recommend monitoring, alerting, backup, and runbook improvements
• Technical walkthrough with SBA Info Solutions
• A support approach for L1 to L3 incidents