Engineering Manager, Site Reliability Engineering

present of AI; Greater London; Hybrid; GBP 120,000 - 170,000; Full time

Job summary

Baseten in London is hiring an Engineering Manager for Site Reliability Engineering to start and lead a new reliability team, guiding engineers while remaining hands-on with critical infrastructure.

You will design resilient systems, own incident response, and mentor staff across time zones as we scale AI inference workloads. Experience with Kubernetes at scale, multi-cloud deployments, and observability-as-code practices will help you succeed.

Qualifications

• Proven leadership experience in SRE or a similar role.
• Strong production Kubernetes experience.
• Experience hiring and coaching engineers.
• Hands-on work with incident response and runbooks.

Responsibilities

• Lead and grow a new reliability team in London while staying hands-on with critical infrastructure.
• Balance people leadership with technical design reviews and cross-team coordination.
• Own incident response, postmortems, and remediation plans.
• Drive observability improvements and codify monitoring and alerting as code.
• Coordinate across time zones to align on incidents and reliability goals.

Skills

Leadership

Kubernetes

Incident response

Observability as code

Multi-cloud infra

Hiring & coaching

Job description

Engineering Manager, Site Reliability Engineering

This role asks for someone to start and lead a new reliability team in London, managing engineers while staying close to the technical work. A strong candidate brings years of hands on Kubernetes and production infrastructure experience, plus a record of hiring, coaching, and running incident response. The job blends people leadership with design reviews, observability work, and cross team coordination across time zones.

How it fits the AI era

The company runs inference for AI models, so reliability work directly supports live AI products. AI tools can help with alerting, log analysis, and drafting runbooks, but judgment during incidents, architectural tradeoffs, and coaching a team stay human. The role rewards people who reduce complexity and turn repeated failures into automated fixes.

How it builds AI experience

Working here means gaining exposure to ML infrastructure and GPU based serving, even though prior machine learning experience is not required. A candidate can build this by learning how inference workloads behave around latency, memory, and GPU use, and by practicing observability as code. Familiarity with incident tooling and multi cloud setups would strengthen the fit.

Worth showing

• Kubernetes at scale
• Team hiring and coaching
• Incident response leadership
• Observability as code
• Multi cloud infrastructure

This is our own read, written from the employer's posting and the company's Spotlight. The employer's posting is the source of truth for the role.

About Baseten

High-performance cloud inference platform for deploying, serving, and scaling open-source and custom artificial intelligence models.