Senior AI Reliability Engineer – Model Serving

Humanloop; Greater London; On-site; GBP 57,000 - 73,000; Full time

Benefits offered by this job

Competitive compensation and benefits

Equity donation matching (optional)

Generous vacation and parental leave

Flexible working hours

Hybrid policy: in-office presence 25%+

Visa sponsorship where possible

Job summary

Anthropic in the UK seeks an experienced reliability-focused engineer to own large-scale AI serving infrastructure. You will define SLAs, build robust monitoring, and drive fast incident response across multiple regions. This role emphasizes cross-team collaboration, ownership, and impact in a highly technical environment.

You should have a strong background in distributed systems, production engineering, or SRE, with a focus on reliability in AI workloads and large-scale model serving.

Qualifications

• Bachelor's degree or equivalent required.
• Experience with distributed systems and reliability concepts.
• Strong communication and collaboration skills; ownership mindset.

Responsibilities

• Define and monitor service level objectives for AI serving systems.
• Design and implement monitoring and observability across token paths.
• Help build high-availability serving infrastructure across regions/clouds.
• Lead incident response for critical AI services and drive improvements.
• Support reliability of safeguard model serving and safety commitments.

Skills

Distributed systems

Reliability engineering

SRE

Communication

Collaboration

Ownership

Open-source contributions

Incident response

Education

Bachelor's degree

Field relevant to role

Tools

AI observability tools

Chaos engineering tooling

Observability frameworks

Large-scale model serving infrastructure

GPU/ML accelerators

Job description

Anthropic in the UK seeks an experienced reliability-focused engineer to own large-scale AI serving infrastructure. You will define SLAs, build robust monitoring, and drive fast incident response across multiple regions. This role emphasizes cross-team collaboration, ownership, and impact in a highly technical environment.

You should have a strong background in distributed systems, production engineering, or SRE, with a focus on reliability in AI workloads and large-scale model serving.