Engineering Manager, Site Reliability Engineering
Baseten is an AI inference platform for deploying, optimizing, and scaling custom, open-source, and fine-tuned models in production.
Funding history
About Baseten
Baseten provides model runtimes, inference infrastructure, developer workflows, and deployment options including managed cloud, self-hosted, and hybrid environments.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will recruit, hire and grow the first SRE team in London, coaching them and setting a high bar. You will own the reliability of multi-cloud Kubernetes infrastructure during your team's hours, lead incident response and post-mortems, and design follow-the-sun on-call rotations with US SRE leadership. You will define SLOs and SLIs, build observability as code, automate mitigations, and partner with other teams.
Requirements
- 4+ years directly managing engineers in SRE, cloud infrastructure or platform engineering
- Extensive hands-on Kubernetes experience
- Background building and maintaining scalable production infrastructure
- Observability tooling: VictoriaMetrics, Prometheus, Loki, ELK, Grafana, alerting
- Infrastructure-as-code (Terraform, Helm) and GitOps (Flux CD, ArgoCD)
- Experience leading incident response, post-mortems, on-call rotations and runbooks
- Track record of recruiting and growing engineering talent
- Strong written and verbal communication across time zones
- Openness to learning ML infrastructure
- Ability to work onsite in London office 3 days a week
Responsibilities
- Recruit, hire and grow the first SRE team in London
- Set performance expectations and foster a culture of ownership and accountability
- Own reliability of multi-cloud Kubernetes infrastructure, including incident response, post-mortems and remediation tracking
- Design follow-the-sun on-call rotations, escalation paths and handoffs with US SRE leadership
- Serve as escalation point for major incidents
- Drive technical decisions through design and code reviews and turn the reliability roadmap into priorities
- Define and instrument SLOs and SLIs and build observability infrastructure as code
- Create runbooks, automated mitigations and self-healing systems
- Partner with engineering, forward deployed, capacity and product teams and report to leadership
- Ensure fleet health across clusters and work with vendors to remediate node failures
Benefits
- Equity
- Flexible PTO policy including company-wide Winter Break
- Paid parental leave
- Fertility and family-building stipend through Carrot
- Exposure to a variety of ML startups