GPFS Storage Engineer for Enterprise HPC

kyndryl; Setiabudi; On-site; IDR 200,000,000 - 320,000,000; Full time

Job summary

Kyndryl is seeking a GPFS Storage Engineer to provide hands-on administration and incident resolution for IBM Spectrum Scale and related storage infrastructure. You will own service restoration for cluster, NSD, path, and node issues, escalating complex cases to SMEs or vendors.

The role emphasizes diagnosing storage problems, restoring critical services, and improving operational resilience within enterprise environments.

Qualifications

• 3-5+ years of enterprise or HPC storage engineering experience, including hands-on Spectrum Scale/GPFS administration.
• Experience with NSDs, quorum, filesets, storage pools, policies, disk/node recovery and Spectrum Scale administration commands.
• Strong Linux troubleshooting and performance-analysis skills.
• Experience with SAN/NAS, Fibre Channel and/or Ethernet/RDMA storage connectivity.
• Ability to analyze IOPS, latency, throughput and capacity trends and distinguish storage symptoms from network or client-side conditions.
• Experience with enterprise storage OEM tooling.
• Formal incident management, change management and root cause analysis experience.

Responsibilities

• Administer Spectrum Scale clusters, filesystems, NSDs, filesets, storage pools and policies within approved change controls.
• Troubleshoot node, disk, NSD, path, mount, quorum and connectivity conditions and restore service using documented recovery procedures.
• Analyze capacity, IOPS, latency and throughput to identify basic storage, network or client-side bottlenecks.
• Use Spectrum Scale mm* commands and vendor/storage tools to collect detailed health and diagnostic data.
• Participate in drive and node replacement, storage hardware recovery, firmware changes and post-change validation.
• Support RDMA/InfiniBand storage paths and collaborate with network teams when transport conditions affect storage performance.
• Execute backup and configuration validation and agreed disaster recovery/recovery procedures.
• Own ticket and SLA progression, maintain technical documentation, contribute to root cause analysis, mentor L1 engineers and improve runbooks.

Skills

GPFS/Spectrum Scale administration

Linux troubleshooting

Storage I/O analysis

SAN/NAS connectivity

RDMA/InfiniBand storage

Tools

Spectrum Scale commands

NSD management

Storage tooling

Job description

Kyndryl is seeking a GPFS Storage Engineer to provide hands-on administration and incident resolution for IBM Spectrum Scale and related storage infrastructure. You will own service restoration for cluster, NSD, path, and node issues, escalating complex cases to SMEs or vendors.

The role emphasizes diagnosing storage problems, restoring critical services, and improving operational resilience within enterprise environments.