Evaluation Reliability SRE

What you'll do

• Own reliability outcomes across the evaluation infrastructure stack, including orchestration, capacity, and service health.
• Author high-quality runbooks for complex failure categories and set the standard for the engineering team.
• Diagnose upstream issues by developing deep expertise in device orchestration, provisioning, and quota management.
• Instrument infrastructure components to improve observability and ensure failures are easily detectable.
• Balance active incident response with proactive reliability work to automate and eliminate recurring failures.
• Define SLOs and burn-rate alerting to turn reliability targets into measurable outcomes.
• Lead end-to-end incident investigations and participate in a global follow-the-sun on-call rotation.
• Influence the technical roadmap and mentor junior SREs on infrastructure reliability practices.

What we're looking for

• 5+ years of site reliability, infrastructure, or platform engineering experience with direct on-call ownership in production systems.
• Hands-on orchestration experience with Kubernetes or equivalent for cluster health, resource management, scheduling, and failure diagnosis at scale.
• Experience owning or closely operating a device or VM provisioning pipeline (preferred).
• Track record of improving system reliability against measurable outcomes like uptime, MTTR, and incident frequency (preferred).
• Incident command discipline to lead multi-team incidents from declaration to close-out (preferred).
• Depth in distributed systems reliability, device management infrastructure, or evaluation/ML platform operations (preferred).
• Demonstrated cross-team technical influence and experience shaping reliability practices beyond the immediate team (preferred).
• Fluency with agentic coding tools like Claude Code, Cursor, or Copilot.