Engineering Manager, Site Reliability Engineering
Core
Build and lead Baseten's first Site Reliability Engineering (SRE) team in London to ensure the reliability of multi-cloud Kubernetes infrastructure for AI companies.
Role type
Engineering Manager, Site Reliability Engineering
Builds
Multi-cloud Kubernetes infrastructure, observability systems, and self-healing mechanisms for AI inference platforms
Domain
Cloud Infrastructure / Site Reliability Engineering / AI Infrastructure
Deliverable
production ML models
Required skills
Team leadership and hiring, Kubernetes architecture, incident response and post-mortems, SLO/SLI definition, observability tooling (metrics, logging, alerting), infrastructure-as-code (Terraform, Helm), GitOps workflows, cross-timezone collaboration
Preferred skills
Building new teams in new regions, multi-cloud/hybrid environment experience, incident management platforms, GPU infrastructure knowledge
Technologies
Kubernetes, EKS, GKE, VictoriaMetrics, Prometheus, Loki, ELK, Grafana, Terraform, Helm, Flux CD, ArgoCD
Responsibilities
Recruit and grow the SRE team, own reliability during team hours, partner on on-call rotations, drive technical decisions and architectural tradeoffs, define observability infrastructure, convert failure patterns into runbooks, partner with other engineering teams
Seniority
Manager, hands-on technical leadership
