Site Reliability Engineer, Siri Evaluation Reliability | Apple | InterviewCat Jobs

業務内容

Own reliability outcomes across the evaluation infrastructure stack: orchestration, capacity, and service health
Own runbook quality across the team: author comprehensive runbooks for complex failure categories
Build deep expertise in device orchestration and provisioning layers — quota management, retry behavior, and failure modes
Instrument infrastructure components lacking observability; make failures detectable before the next occurrence
Balance incident response with proactive reliability work: automation and eliminating recurring failures
Define and monitor SLOs; collaborate on burn-rate alerting to turn targets into measurable outcomes
Influence the technical roadmap; mentor junior SREs; represent reliability posture to leadership and cross-team reviews
Participate in a global follow-the-sun on-call rotation; lead end-to-end incident investigations

5+ years of site reliability / infrastructure / platform engineering with on-call in production
Hands-on orchestration experience (Kubernetes or equivalent): cluster health, resource management, scheduling, failure diagnosis
Experience owning or operating a device or VM provisioning pipeline; familiarity with virtualization-layer failure modes
Track record of improving reliability with measurable outcomes (uptime, MTTR, incident frequency)
Incident command discipline: lead multi-team incidents from declaration to close-out
Depth in at least one area: distributed systems reliability, device management infrastructure, evaluation or ML platform operations
Demonstrated cross-team technical influence; ability to shape reliability practices beyond the immediate team

Experience with agentic coding tools (Claude Code, Cursor, Copilot) to enhance runbooks, automation, and log analysis
Exposure to ML evaluation infrastructure or ML platform operations
Ability to influence reliability roadmap and communicate effectively with leadership