SRE for AI Platform Reliability & Observability

Callosum; Greater London; On-site; GBP 90,000 - 150,000; Full time

Benefits offered by this job

Equity & Ownership

Private healthcare

Visa sponsorship & relocation

London office

Job summary

Callosum is building the next generation of AI infrastructure in London. We own the production system through end-to-end health, SLOs, observability, and incident response, across heterogeneous compute backends.

You will set the direction for reliability and partner with platform and hardware teams to keep systems resilient at scale. You will drive capacity planning, on-call readiness, and deployment discipline in a fast-growing environment, ensuring production-grade operations for real traffic

Qualifications

• Strong SRE/production-engineering background with experience running customer-facing systems at scale.
• Fluency with modern operational tooling, including observability stacks and container orchestration.
• Experience owning incident response and driving reliability improvements.
• Familiarity with compliance execution and security controls.

Responsibilities

• Own the platform's operational health end-to-end, including SLOs and capacity planning.
• Define production-grade standards and drive reliability across heterogeneous backends.
• Collaborate with platform, hardware, and orchestration teams to expose backends reliably.
• Lead on-call, runbooks, blameless postmortems, and incident follow-ups.

Skills

SRE / Production Engineering

Observability & Monitoring

Incident response

CI/CD & Deployment

Tools

Kubernetes

CI/CD

Infrastructure as Code

Observability stacks

Job description

Callosum is building the next generation of AI infrastructure in London. We own the production system through end-to-end health, SLOs, observability, and incident response, across heterogeneous compute backends.

You will set the direction for reliability and partner with platform and hardware teams to keep systems resilient at scale. You will drive capacity planning, on-call readiness, and deployment discipline in a fast-growing environment, ensuring production-grade operations for real traffic