Staff AI Reliability Engineer: Scalable Serving

Anthropic; Dublin; Hybrid; EUR 235,000 - 295,000; Full time

Benefits offered by this job

Competitive compensation

Flexible working hours

Generous vacation and parental leave

Job summary

A technology company located in Dublin is seeking an experienced candidate to join their AIRE Serving team. This role focuses on enhancing the reliability of AI systems through effective management of model serving infrastructure. Responsibilities include developing service level objectives, designing monitoring systems, and leading incident responses. Suitable applicants should possess a Bachelor's degree, extensive experience with distributed systems, and the ability to communicate effectively across teams. The annual salary ranges from €235,000 to €295,000, with a hybrid work policy.

Qualifications

• Extensive experience with distributed systems observability and monitoring at scale.
• Understanding of the unique challenges of operating AI infrastructure.
• Proven experience implementing SLO/SLA frameworks.

Responsibilities

• Develop appropriate Service Level Objectives for model serving.
• Design and implement monitoring systems including availability and latency metrics.
• Lead incident response for critical AI services.

Skills

Distributed systems observability

AI infrastructure management

SLO/SLA frameworks

Communication skills

Chaos engineering

Education

Bachelor's degree in a related field

Tools

AI-specific observability tools

ML hardware accelerators

Job description

A technology company located in Dublin is seeking an experienced candidate to join their AIRE Serving team. This role focuses on enhancing the reliability of AI systems through effective management of model serving infrastructure. Responsibilities include developing service level objectives, designing monitoring systems, and leading incident responses. Suitable applicants should possess a Bachelor's degree, extensive experience with distributed systems, and the ability to communicate effectively across teams. The annual salary ranges from €235,000 to €295,000, with a hybrid work policy.