Evaluation Reliability SRE

Join the team redefining what a deeply personal and integrated assistant can be. As part of the Siri organization, you will help shape one of the world's most widely used AI assistants, powered by our next-generation of Apple Intelligence, with capabilities like personal context understanding and on-screen awareness, built with privacy from the ground up. Your work will have direct, meaningful impact for users across iOS, iPadOS, macOS, watchOS, and visionOS. This is a rare opportunity to build at the intersection of cutting-edge AI and human-centered design, shipping technology that is centered around users and their needs.

Description

Siri’s quality signal drives every model and product decision before a release ships. But a signal is only as trustworthy as the infrastructure behind it.

The Evaluation Reliability Engineering (ERE) team exists to make that infrastructure bulletproof. Within ERE, Core SRE owns the production backbone: resource management, session orchestration, on-call response, and the observability systems that surface failures before they corrupt evaluation signal. We sit at the intersection of distributed systems, ML evaluation infrastructure, and operational excellence.

This is a senior hands-on role. You share primary on-call as part of a global follow-the-sun rotation, lead incident investigations end-to-end, and set the operational bar the rest of the team works against. You are fluent with agentic coding tools like Claude Code, Cursor, or Copilot, and use them as a force multiplier across runbook authoring, automation, and log analysis.

Minimum Qualifications

5+ years of site reliability, infrastructure, or platform engineering experience with direct on-call ownership in production systems
Hands-on orchestration experience (Kubernetes or equivalent): cluster health, resource management, scheduling, and failure diagnosis at scale

Preferred Qualifications

Experience owning or closely operating a device or VM provisioning pipeline; familiarity with virtualization-layer failure modes is a strong plus
Track record of improving system reliability against measurable outcomes — uptime, MTTR, incident frequency — not just responding to incidents but eliminating their causes
Incident command discipline: able to lead a multi-team incident from declaration to close-out
Depth in at least one of: distributed systems reliability, device management infrastructure, evaluation or ML platform operations
Demonstrated cross-team technical influence; prior experience shaping reliability practices beyond the immediate team