Engineering Manager, Site Reliability Engineering

RESPONSIBILITIES

• Recruit, hire, and grow Baseten’s first SRE team in London, with ongoing coaching, feedback, and career development through regular 1:1s.

• Set clear performance expectations, hold a high bar, and foster a culture of ownership, accountability, and continuous improvement.

• Own the reliability of Baseten’s multi-cloud Kubernetes infrastructure during your team’s hours, including incident response, post-mortems, and remediation tracking.

• Partner with SRE leadership in the US to design follow-the-sun on-call rotations, escalation paths, and handoff processes.

• Serve as the escalation point for major incidents, drive resolution with urgency, and make sure the team learns from every incident.

• Drive technical decisions through design reviews, code reviews, and architectural discussions. Turn the reliability roadmap into clear team priorities and milestones, and hold the team accountable for delivering them.

• Lead the team in defining and instrumenting SLOs and SLIs, and in building observability infrastructure (metrics, logging, dashboards, and alerting) as code.

• Turn recurring failure patterns and tribal knowledge into runbooks, automated mitigations, and self-healing systems.

• Partner with engineering, forward deployed, capacity, and product teams to raise the operational floor across the company, and represent your team’s progress, capacity, and tradeoffs clearly to leadership.

• Ensure the fleet is healthy and operational across all clusters. Interact with vendors and internal teams to remediate node failures and reliability concerns.

• Exercise and encourage good judgment on tooling and architectural tradeoffs, with a bias against unnecessary complexity.

REQUIREMENTS

• 4+ years of experience directly managing engineers in an SRE, cloud infrastructure, or platform engineering context.

• Extensive hands-on experience with Kubernetes, with the ability to engage credibly in architectural discussions and code reviews (multi-cloud experience across EKS, GKE, or similar is a strong plus).

• Strong background building and maintaining scalable production infrastructure.

• Strong foundation in observability tooling: metrics (VictoriaMetrics, Prometheus), logging (Loki, ELK), dashboards (Grafana), and alerting pipelines.

• Experience with infrastructure-as-code (Terraform, Helm) and GitOps workflows (Flux CD, ArgoCD).

• Experience leading incident response, running post-mortems, and building on-call rotations and runbooks.

• Track record of recruiting and growing engineering talent.

• Strong written and verbal communication skills, with the ability to collaborate across time zones and influence without direct authority.

• Openness to learning about ML infrastructure. Prior machine learning experience is not required.

• Ability to work onsite in our London office 3 days a week.

NICE TO HAVE

• Experience building a new team or establishing an engineering presence in a new region.

• Observability-as-code experience.

• Background in multi-cloud and hybrid environments.

• Familiarity with incident management platforms (incident.io or similar).

• Background in GPU infrastructure, or in diagnosing runtime issues around latency, memory behaviour, GPU utilisation, and concurrency.

BENEFITS

• Competitive compensation, including meaningful equity

• Paid parental leave

• Fertility and family-building stipend through Carrot

• (U.S. only) Company-facilitated 401(k)