Data Center Support Engineer

Nebius is seeking a Data Center Support Engineer to support large scale bare metal GPU infrastructure powering AI workloads. This role is responsible for operating, troubleshooting, and maintaining production infrastructure across servers, Linux systems, networking, firmware, drivers, and physical data center components.

You will serve as a senior technical escalation point between data center technicians, infrastructure engineering, network engineering, systems engineering, and customer facing teams. The ideal candidate is hands on, comfortable in Linux, strong in hardware diagnostics, and able to troubleshoot complex issues across multiple layers of the infrastructure stack.

- Support and troubleshoot production bare-metal GPU infrastructure across Nebius data center environments.

- Diagnose high-priority issues across Linux, hardware, firmware, BIOS, drivers, networking, storage, optics, cabling, and physical infrastructure.

- Perform hardware diagnostics, component replacement, firmware updates, BIOS configuration, break/fix, and infrastructure maintenance.

- Use Linux command-line tools, system logs, BMC data, and hardware health signals to identify root cause.

- Partner with data center technicians and engineering teams to coordinate remote troubleshooting, incident response, RCA, and operational recovery.

- Troubleshoot network connectivity issues involving TCP/IP, VLANs, DNS, DHCP, switch connectivity, optics, cabling, and link-level failures.

- Create troubleshooting guides, runbooks, escalation notes, and knowledge base documentation.

- Use scripting or automation to improve support workflows and reduce manual intervention.

- Participate in on-call or after-hours support for production infrastructure as needed.

- 5+ years of experience in data center operations, infrastructure support, systems administration, hardware support, cloud infrastructure, or similar technical environments.

- Hands-on experience troubleshooting bare metal servers, Linux systems, hardware components, and networking issues in production environments.