Server NPU Infrastructure Engineer

You will build and operate NPU server hardware, perform rack installation and physical configuration changes, manage BIOS, BMC, and firmware settings, and monitor hardware health. You will diagnose and recover from faults, manage assets and vendor RMA activities, maintain operating procedures, and support capacity planning.

Responsibilities

• Build and operate NPU server hardware.
• Install, rack, relocate, and retire servers.
• Install, replace, and reconfigure NPU cards.
• Manage BIOS, BMC, and firmware configurations and validate server compatibility.
• Monitor server temperature, power, fans, disks, and NPU status and respond to alerts.
• Diagnose hardware faults, replace parts, and restore service.
• Manage incident severity, incident records, and vendor RMA communication.
• Maintain server and component inventory records.
• Perform regular inspections and report results.
• Create and maintain emergency-response and operating procedures.
• Support capacity planning for rack space and power.
• Work onsite during the day and participate in an on-call rotation for nights and weekends.

Requirements

• 3+ years of server-infrastructure operations experience.
• Knowledge of x86 server hardware, including CPU, memory, PCIe, storage, and power.
• Experience with BMC-based remote server management using IPMI or Redfish.
• Data-center equipment installation and operations experience.
• Linux operations skills, including log review and hardware diagnostic tools.
• GPU or NPU server operations experience.
• Large-scale server-farm operations experience.
• Monitoring-system experience with Prometheus, InfluxDB, Zabbix, or Grafana.
• Bash or Python automation scripting skills.
• Vendor and RMA process experience.