Site Reliability Engineer
Baseten · San Francisco
About this role
**Site Reliability Engineer** **About Baseten** Baseten powers mission-critical inference for leading AI companies like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer. We recently raised our $1.5B Series F and are building the platform engineers use to ship AI products. **The Role** Define and codify operational excellence for our ML infrastructure platform. You'll build robust systems, processes, automations, and observability tooling that keep our platform reliable at scale while empowering the broader organization. **Key Responsibilities** • Own reliability of multi-cloud Kubernetes infrastructure, incident response, and remediation • Build and maintain observability infrastructure (metrics, logging, dashboards, alerting) as code • Author and improve runbooks for recurring failure patterns • Convert high-frequency failures into automated mitigations • Diagnose runtime issues (latency, memory, GPU utilization, concurrency, model lifecycle) • Define and instrument SLOs/SLIs across workloads and services **Requirements** • Extensive hands-on Kubernetes experience (multi-cloud: EKS, GKE, etc.) • Scalable infrastructure building and maintenance • Strong observability foundation (Prometheus, VictoriaMetrics, Loki, Grafana) • Infrastructure-as-code (Terraform, Helm) and GitOps (Flux CD, ArgoCD) • Runbook writing, incident response, and post-mortem experience • Comfort at engineering/operations intersection • ML deployment curiosity (no prior ML experience required) **Benefits** • Competitive compensation with meaningful equity • 100% medical, dental, vision coverage (U.S.) • Flexible PTO + company Winter Break • Paid parental leave • Family-building stipend (Carrot) • 401(k) facilitation (U.S.) **Equal Opportunity Employer** - We welcome qualified applicants from all backgrounds.
Listing freshness
CronJobs last confirmed this listing 2h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.