Staff AI Reliability Engineer – LLM Serving

SignalAI

Dublin

Hybrid

EUR 235,000 - 295,000

Full time

7 days ago

Be an early applicant

Get more replies from employers

Send a job-specific resume in minutes.

Benefits offered by this job

Equity donation matching

Generous vacation

Parental leave

Flexible working hours

Office space

Job summary

Anthropic seeks an AI Reliability Engineer to help keep Claude reliable across serving paths from the SDK to network and infrastructure. You will join a cross-functional team focusing on robust, scalable systems and incident response.

The role emphasizes collaboration with engineers, researchers, and operators to sustain high availability and safety commitments. You will design SLIs/SLOs, implement comprehensive monitoring, and lead incident reviews across regions and cloud providers to

Qualifications

Strong background in distributed systems, infrastructure, or reliability.
Willingness to jump into unfamiliar systems during incidents and drive resolution.
Ability to think holistically about system composition and seams.
Experience collaborating across multiple teams and stakeholders.

Responsibilities

Develop Service Level Objectives for large language model serving systems, balancing availability and latency with development velocity.
Design and implement monitoring and observability across the token path.
Assist in high-availability serving infrastructure across regions and clouds.
Lead incident response for critical AI services, ensuring rapid recovery and thorough post-incident reviews.
Support reliability of safeguard model serving and safety commitments.