Tier 1 NOC Engineer (HPC & Bare-Metal Infrastructure)

We are seeking a technical, detail-oriented Tier 1 NOC Engineer to join our 24/7 Operations team. In this role, you will serve as the first line of defense for our global high-performance computing (HPC) bare-metal infrastructure, high-speed InfiniBand fabrics, and parallel storage systems. You will actively monitor cluster telemetry, perform rapid triage on live alerts, execute initial Linux OS and hardware troubleshooting, and coordinate on-site remote-hands data center technicians to maintain sub-15 minute SLA response targets. Core Responsibilities1. 24/7 Monitoring & Alert Triage Actively monitor global HPC clusters, bare-metal GPU/CPU nodes, network fabrics, and storage arrays using Grafana, Prometheus, and internal telemetry tools. Validate, categorize, and perform initial incident triage for automated alerts and customer ticket submissions. Ensure strict adherence to response time SLAs for critical hardware, OS, and network outages.2. Hardware & Infrastructure Troubleshooting Perform initial diagnostics on x86 bare-metal servers, inspect Out-of-Band (OOB) management interfaces (IPMI, Redfish, iDRAC/iLO), and review hardware logs. Identify component-level hardware failures, including GPU/PCIe errors, DIMM faults, drive dropouts, power supply failures, and thermal anomalies. Open, track, and direct vendor dispatch tickets (e.g., Supermicro, Dell, HPE, NVIDIA) for physical hardware replacements.3. Linux OS & Network Isolation Access non-responsive or degraded hosts via serial-over-LAN/SSH to inspect system logs (dmesg, syslog, journalctl).Check basic Layer 1–Layer 3 network connectivity, interface link states, IP assignment, and optical transceiver signal levels. Escalate complex fabric routing, InfiniBand subnet manager, or parallel storage issues to Tier 2/3 HPC and Network Engineers with clean, structured diagnostic notes.4. Remote-Hands Coordination & Dispatch Direct on-site data center technicians for physical cable pulls, server reboots, drive swaps, and component replacements. Track hardware RMA lifecycles from fault identification to physical repair verification and host re-commissioning.5. Incident Documentation & Runbooks Maintain detailed, real-time ticket notes documenting all troubleshooting steps, root causes, and resolutions. Follow established operational runbooks and assist in updating Standard Operating Procedures (SOPs) as new issues emerge.