HPC Storage Engineer

TL;DR

HPC Storage Engineer (Lustre/GPFS/BeeGFS): Designing, operating, and optimizing high-throughput parallel filesystems for demanding compute workloads with an accent on I/O performance tuning and operational resilience. Focus on diagnosing complex metadata bottlenecks, automating lifecycle management, and ensuring high availability for AI/ML and science workloads.

Location: Remote

Company

hirify.global provides specialized high-performance computing operations and infrastructure engineering.

What you will do

• Deliver stable, high-performance parallel filesystem services using Lustre, IBM Spectrum Scale (GPFS), or BeeGFS.
• Optimize throughput, latency, and metadata performance through data-path tuning and evidence-based benchmarking.
• Design and evolve filesystem architectures, including MDS/MDT, OSS/OST, targets, pools, and tiering.
• Perform detailed I/O performance analysis using tools such as IOR, mdtest, and fio to validate architectural changes.
• Automate repeatable builds, patching, and health checks using Ansible and scripting.
• Collaborate with HPC, networking, and platform teams to align storage behavior with real workload patterns.

Requirements

• 3–7+ years of experience operating and supporting HPC storage platforms and parallel filesystems in production.
• Strong Linux administration skills (RHEL/Rocky/Ubuntu), including performance tuning and troubleshooting.
• Proven expertise in the installation, upgrade, and day-2 operations of Lustre, IBM Spectrum Scale (GPFS), or BeeGFS.
• Deep understanding of RDMA, InfiniBand, NVMe, and RAID fundamentals.
• Proficiency in automation and scripting using Bash and/or Python.
• Fluent English (written and spoken) for cross-team collaboration and documentation.

Nice to have

• Experience with HPC schedulers such as Slurm.
• Familiarity with object storage (S3) or HSM tiering concepts.
• Exposure to HPC containers including Apptainer, Singularity, or Docker.