Senior HPC Engineer - GPU/Cluster Ops (Hybrid)

University of California San Diego; San Diego (CA); Ibrido; USD 130.000 - 164.000; Tempo pieno

Descrizione del lavoro

UC San Diego is seeking a Sr. High-Performance Computing (HPC) Engineer to lead the technical operation of AWARE, CW3E’s HPC system.

You will own system administration, maintenance, upgrades, deployments and troubleshooting to ensure high availability for real-time forecasting and research. Responsibilities include managing compute and GPU nodes, networks, storage, job scheduling, authentication, monitoring, and data transfers.

Competenze

• Advanced knowledge of deploying and integrating complex HPC systems.
• Experience with system integration design in large, multi-platform environments.
• Ability to plan deployments, upgrades and storage solutions with minimal downtime.
• Experience supporting HPC clusters, Linux systems (Red Hat derivatives) and networking.
• Ability to mentor staff and communicate with both technical and non-technical stakeholders.

Mansioni

• Lead system administration, maintenance, upgrades, and troubleshooting for the AWARE HPC system.
• Manage compute and GPU nodes, networks, storage, and job scheduling with emphasis on availability.
• Coordinate with campus teams and vendors; document changes and procedures.

Conoscenze

High-performance computing

System administration

Linux cluster management

Networking expertise

Scripting (Python, Bash)

MPI/parallel computing

Research computing support

Strumenti

Slurm

BeeGFS

Lustre

GPFS

ZFS

Descrizione del lavoro

UC San Diego is seeking a Sr. High-Performance Computing (HPC) Engineer to lead the technical operation of AWARE, CW3E’s HPC system.

You will own system administration, maintenance, upgrades, deployments and troubleshooting to ensure high availability for real-time forecasting and research. Responsibilities include managing compute and GPU nodes, networks, storage, job scheduling, authentication, monitoring, and data transfers.