Principal Engineer, AI Inference Reliability

Own the reliability mission for AI inference services, spanning client SDKs, public-cloud multi-region deployments, and wafer-scale systems in specialized data centers. Define SLOs and incident-response frameworks, design reliability mechanisms for fault detection, graceful degradation, failover, throttling, and recovery, and lead postmortems and prevention loops. Build reliability dashboards and tooling for chaos testing and distributed fault injection, and mentor engineers to embed reliability across every layer of the inference stack.