Server Hardware Systems Engineer (Starlink)
SpaceX · Hawthorne, CA
About this role
**SpaceX — Server Hardware Systems Engineer (Starlink)** Starlink delivers high-speed, low-latency internet to millions worldwide. The network relies on a global fleet of servers running in data centers and points of presence (PoPs). The Starlink Site Reliability Engineering (SRE) team is hiring a **Server Hardware Systems Engineer** to own the health of this fleet as it scales rapidly. You’ll own the server hardware lifecycle—from **issue detection**, through **repair**, to **recovery**. You’ll build the **telemetry, alerting, and automation** that enable a small team to operate a very large fleet, and you’ll coordinate with network operations, field technicians, hardware vendors, and data center partners to get failed hardware repaired and back into service quickly. You’ll also use fleet reliability data to shape **server design, selection, and qualification** for new sites across both **COTS** and **custom-designed** server platforms. This role is primarily office-based (not in data center facilities), but you’re encouraged to spend time in the field with Starlink data center engineering teams. --- ### Responsibilities - **Own the end-to-end hardware repair lifecycle** for the Starlink server fleet and components (CPUs, memory, SSDs, NICs, optics, power supplies): triage alerts, isolate failures to the component level, and drive safe removal from production, repair, validation, and return to service. - **Manage vendor support cases** and coordinate on-site work with data center remote hands and field technicians (parts delivery, site access, and return of failed parts for warranty replacement or failure analysis). - **Build the software and automation** behind the repair path: hardware telemetry and alerting (BMC/Redfish exporters, node-level metrics, log collection), removal of manual diagnostics steps, production drain/return, alert silencing, post-repair validation, and component-level tracking from detection to recovery. - **Define, measure, and report fleet hardware metrics**, including Mean Time to Respond/Repair/Recover (p50 and p90), backlog trends, and component failure rates; publish regular status updates to stakeholders. - **Write runbooks, methods of procedure (MOPs), and training material** so NOC and field technicians can resolve common hardware incidents. - **Validate new server hardware** before it is deployed (details continue in the source description).
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.