Staff AI Reliability Engineer — Large-Scale Systems

Anthropic Limited; New York (NY); On-site; USD 325,000 - 485,000; Full time

Job summary

Anthropic Limited is seeking an AI Reliability Engineer (AIRE) to partner with teams across Anthropic to improve reliability of Claude's serving paths.

You will define SLOs, design monitoring, lead incident response, and help build high-availability infrastructure across regions, with a focus on safety and observability.

Join a team that emphasizes reliability, collaboration, and scalable systems for a safer AI future.

Qualifications

• Bachelor’s degree or equivalent in a relevant field.
• Experience with large-scale distributed systems and reliability.
• Strong communication and collaboration across teams.

Responsibilities

• Develop appropriate Service Level Objectives for large language model serving systems, balancing availability and latency with development velocity.
• Design and implement monitoring and observability systems across the token path.
• Assist in the design and implementation of high-availability serving infrastructure across multiple regions and cloud provider.
• Lead incident response for critical AI services, ensuring rapid recovery, thorough incident reviews, and systematic improvements.
• Support the reliability of safeguard model serving – critical for both site reliability and Anthropic's safety commitments.

Skills

Distributed systems

SRE

Observability

Incident response

Education

Bachelor’s degree or equivalent in a relevant field

Tools

Observability tooling (Prometheus, Grafana)

Cloud infrastructure (AWS/GCP/Azure)

Job description

Anthropic Limited is seeking an AI Reliability Engineer (AIRE) to partner with teams across Anthropic to improve reliability of Claude's serving paths.

You will define SLOs, design monitoring, lead incident response, and help build high-availability infrastructure across regions, with a focus on safety and observability.

Join a team that emphasizes reliability, collaboration, and scalable systems for a safer AI future.