Senior HPC Systems Engineer

You will act as a senior escalation point for infrastructure incidents, diagnose GPU, network, and storage faults, and deliver safe changes in live customer environments. You will improve monitoring, runbooks, and automation; communicate incident impact clearly; mentor engineers; participate in on-call support; and travel to sites when required.

Responsibilities

• Serve as a senior escalation point for incidents, investigations, and changes
• Diagnose and remediate GPU node faults across driver, firmware, hardware, and management layers
• Maintain and troubleshoot InfiniBand, RoCE, and high-speed Ethernet fabrics
• Investigate high-performance storage data-path issues
• Conduct root cause analyses and drive long-term fixes
• Author and execute risk-assessed production changes with backout plans
• Improve dashboards, alerts, runbooks, and operational automation
• Record and resolve tickets with clear customer-impact updates
• Mentor mid-level engineers and contribute training and reviews
• Participate in on-call support and travel to sites as required

Requirements

• 6+ years of infrastructure, operations, or support engineering experience
• 2–3+ years of hands-on GPU, HPC, or large-scale data center experience
• NVIDIA GPU platforms, drivers, firmware, nvidia-smi, DCGM, and XID analysis
• InfiniBand or RoCE RDMA fabrics
• Slurm, Pyxis/Enroot, MPI, and multi-GPU job troubleshooting
• Linux systems engineering
• BMC, Redfish, and bare-metal provisioning
• L2/L3 networking, routing, BGP, VLANs, VXLAN, firewalls, and load balancing
• Prometheus or Grafana
• Bash or Python scripting
• Git and infrastructure automation tools such as Ansible or Terraform
• Data center operations