Backend Engineering Manager, Cloud Inference

Lead and grow a team building cloud inference backend systems that power large-scale LLM inference on Kubernetes. Own operational excellence across on-call readiness, incident response, SLOs, alerts, and runbooks, while establishing engineering best practices for design reviews, testing, and safe rollouts. Partner with product and adjacent engineering orgs to deliver distributed inference services with improved reliability, latency, throughput, performance, and operational maturity.