Site Reliability Engineer, Provider Operations

You will own the operational health of provider endpoints. You will build monitoring, define SLOs, improve detection and automated failover, and lead incident response. You will create quality canaries, automate provider-operations tasks, produce provider scorecards, and load-test endpoints before launches.

Responsibilities

• Build and own monitoring for provider and endpoint latency, throughput, error rates, uptime, and output correctness
• Set provider-tier SLOs and actionable alerts
• Improve degraded-endpoint detection and enable automatic traffic failover
• Lead provider incident response, including triage, mitigation, provider communication, postmortems, and follow-ups
• Create provider scorecards and SLO reporting
• Build continuous canaries and evaluations to detect quality regressions
• Automate manual provider-operations work with safe, auditable tooling
• Build endpoint load-testing tooling for launch readiness

Requirements

• 4+ years in SRE, production engineering, or infrastructure roles supporting high-traffic customer-facing systems
• Observability expertise, including metrics, tracing, logs, SLOs, error budgets, and alerting
• Software engineering ability with TypeScript and/or Python
• Knowledge of distributed-systems failure modes
• Incident-command and external-partner communication skills
• Knowledge of, or willingness to learn, LLM inference serving