Onsite HPC Systems Engineer - GPU Cluster Expert

Motorsport Network, LLC; Concord (NC); On-site; USD 110,000 - 160,000; Full time

Benefits offered by this job

Bonus scheme

Private healthcare

401(k) plan including company match

Employer-paid life insurance and dis­-

32 days annual leave (including HOLID"

Free financial advisor access

Employee Assistance Programs (EAP)

On-site gym

Subsidized on-site dining

Discounted GM vehicle purchase/lease

Job summary

GM Performance Power Units in Concord, NC is seeking an HPC Systems Engineer to own the operation and optimization of production and development HPC clusters supporting CAE, CFD, and FEA simulations. You will patch, monitor, and maintain NVIDIA GPU nodes, administer Slurm, and ensure licensing and storage services run reliably.

You will install and maintain CFD/FEA software environments, assist users with job scripts, diagnose performance issues, and write automation scripts.

Qualifications

• Experience administering Linux servers in a datacenter or HPC environment.
• Familiarity with Slurm or similar workload managers and cluster tooling.
• Knowledge of NVIDIA GPU drivers and base command software.
• Scripting in Bash and Python for automation and health checks.
• Strong networking fundamentals including RDMA/InfiniBand.
• Experience with MPI tuning and NUMA topology for performance.
• NFS or shared filesystem administration experience.
• Familiarity with CFD/FEA software environments.

Responsibilities

• Own day-to-day operation, maintenance, and optimization of HPC clusters.
• Patch, image, update drivers/firmware, and monitor node health.
• Administer Slurm: partitions, QoS, accounting, reservations.
• Manage NFS storage, quotas, and permissions.
• Administer license servers and enforce license limits.
• Install/maintain commercial CFD/FEA software and environment modules.
• Provide user support: troubleshooting, onboarding, documentation.
• Diagnose performance issues and benchmark node/fabric performance.
• Develop shell scripts for automation, reporting, and tooling.
• Handle vendor tickets through resolution and support capacity expansion.

Skills

Linux admin

Slurm

GPU management

Bash scripting

Python scripting

Networking (RDMA/InfiniBand)

MPI tuning

NFS administration

CFD/FEA familiarity

Tools

Bright Cluster Manager

NVIDIA Base Command Manager

FlexLM / RLM licensing

Job description

GM Performance Power Units in Concord, NC is seeking an HPC Systems Engineer to own the operation and optimization of production and development HPC clusters supporting CAE, CFD, and FEA simulations. You will patch, monitor, and maintain NVIDIA GPU nodes, administer Slurm, and ensure licensing and storage services run reliably.

You will install and maintain CFD/FEA software environments, assist users with job scripts, diagnose performance issues, and write automation scripts.