HPC Storage Architect for Large-Scale Data & AI

UCSF Health; San Francisco (CA); On-site; USD 140,000 - 190,000; Full time

Job summary

UCSF is seeking a Storage Systems Engineer to design, deploy, and operate large-scale storage for FAC and related platforms, ensuring seamless integration with the CoreHPC compute cluster. This role supports AI, data science, and computational research workloads across on-premises and hybrid environments.

The position emphasizes data movement tooling, performance tuning, and collaboration with DevOps, networking, and security teams. Experience with ZFS, VAST, and HPC schedulers is essential.

Qualifications

• Bachelor's degree in computer science or engineering with 6+ years of storage infra experience, or 10+ years in large-scale storage systems.
• 5+ years deploying, managing, and troubleshooting ZFS or similar InfiniBand-based clusters.
• Strong knowledge of ZFS, high-performance parallel filesystems, and storage such as GPFS, Lustre, Vast, DDN.
• Advanced knowledge of computer security practices and policies, including NIST 800-171/800-223, HIPAA, IS-3.
• Knowledge of HPC job scheduler systems such as SLURM or PBS.

Responsibilities

• Design, deploy, and operate large-scale storage systems, including ZFS, VAST, and parallel filesystems.
• Define standards for performance, redundancy, and scalability on ZFS filesystems.
• Lead evolution of institutional storage platforms (FAC storage), primarily ZFS.
• Manage Active Directory integration with storage and compute systems.
• Architect and execute large-scale data migrations.
• Develop data movement workflows using rsync, rclone, Globus.

Skills

Storage architecture design

HPC integration

Data movement tooling

Performance tuning

Collaboration with DevOps/Networking/S

Education

Bachelor's degree in computer science or engineering

Tools

ZFS

VAST

Lustre

GPFS

DDN

InfiniBand

SLURM/PBS

Active Directory integration

VMware

Job description

UCSF is seeking a Storage Systems Engineer to design, deploy, and operate large-scale storage for FAC and related platforms, ensuring seamless integration with the CoreHPC compute cluster. This role supports AI, data science, and computational research workloads across on-premises and hybrid environments.

The position emphasizes data movement tooling, performance tuning, and collaboration with DevOps, networking, and security teams. Experience with ZFS, VAST, and HPC schedulers is essential.