Storage Engineer

Job Summary

The IBM Spectrum Scale (GPFS) Administrator will be responsible for the administration, configuration, troubleshooting, and optimization of enterprise-scale storage environments, with a strong focus on IBM Spectrum Scale (GPFS) and Linux-based infrastructure. The role involves managing GPFS clusters, filesystems, NSDs, storage pools, policies, quotas, replication, and high-availability configurations.

The position requires strong hands-on expertise in GPFS architecture, SAN/NAS storage, NFS/SMB, RAID, LVM, multipathing, and Linux storage administration, along with the ability to troubleshoot complex storage, performance, networking, and filesystem issues. The candidate will monitor cluster health and storage performance, perform upgrades and capacity expansions with minimal disruption, and conduct detailed root-cause analysis (RCA) for storage incidents.

The role will also collaborate closely with server, network, operating system, application, and HPC/AI teams to deliver reliable and high-performance storage solutions. Experience with HPC/AI environments, Slurm, Kubernetes/OpenShift, InfiniBand/RDMA, or high-speed Ethernet will be an added advantage. Strong scripting, automation, documentation, and incident-management skills are expected.

Key Responsibilities:

• Hands-on administration and troubleshooting of IBM Spectrum Scale (GPFS) environments.
• Install, configure, upgrade, and maintain GPFS clusters, filesystems, NSDs, and storage pools.
• Configure and troubleshoot GPFS nodes, quorum/manager nodes, NSD servers, and client nodes.
• Manage GPFS filesystem creation, mounting, policies, quotas, replication, and performance tuning.
• Troubleshoot GPFS issues related to I/O performance, node failures, filesystem availability, disk/NSD failures, and network connectivity.
• Strong understanding of SAN, NAS, NFS, SMB, Fibre Channel, iSCSI, and Ethernet storage networks.
• Experience with Linux storage administration, LVM, multipathing, RAID, disk management, and filesystem troubleshooting.
• Monitor storage capacity, IOPS, latency, throughput, and overall cluster health.
• Perform GPFS upgrades, patches, configuration changes, and capacity expansion with minimum service disruption.
• Analyze GPFS logs and Linux system logs and perform root-cause analysis for storage incidents.
• Work with server, network, OS, and application teams for end-to-end storage issue resolution.
• Prepare technical documentation, RCA, health reports, and operational procedures.

Mandatory Skills

• Strong hands-on experience in IBM Spectrum Scale / GPFS
• Linux administration, preferably RHEL
• GPFS architecture, NSD, quorum, CES, filesets, pools, and policies
• SAN/NAS storage concepts
• RAID, LVM, multipathing, NFS/SMB
• Storage performance monitoring and troubleshooting
• Shell scripting and basic automation
• Good troubleshooting and incident-management skills.

Good to Have

• Experience with HPC/AI/GPU infrastructure
• GPFS integration with Slurm, Kubernetes/OpenShift, or HPC clusters
• Experience with InfiniBand/RDMA or high-speed Ethernet
• Experience with enterprise storage platforms such as Dell, NetApp, Lenovo, HPE, or IBM
• IBM Spectrum Scale certification or equivalent hands-on experience