Staff AI Reliability Engineer – Scale, Resilience & Observability

Mat Vin; Greater London; Ibrido; GBP 325.000 - 390.000; Tempo pieno

Descrizione del lavoro

Anthropic is seeking a Staff Software Engineer in London to strengthen AI reliability engineering across serving paths, from SDK to network and infrastructure. You will lead incident response, design robust monitoring, and work with cross-team partners to ensure Claude’s reliability and performance.

The role emphasizes building scalable, high-availability systems with global reach and a strong emphasis on safety commitments and observability tooling.

Competenze

• Bachelor’s degree or equivalent required.
• Experience with large-scale distributed systems and reliability.
• Experience operating large-scale model serving infrastructure.

Mansioni

• Develop 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 providers.
• Lead incident response for critical AI services, ensuring rapid recovery, thorough incident reviews, and systematic improvements.
• Support the reliability of safeguard model serving and safety commitments.

Conoscenze

Distributed systems

Reliability engineering

Incident response

Cross-team collaboration

Communication skills

Formazione

Bachelor’s degree or equivalent

Strumenti

Model serving infra

GPUs/TPUs hardware

RDMA/InfiniBand

ML observability tools

Descrizione del lavoro

Anthropic is seeking a Staff Software Engineer in London to strengthen AI reliability engineering across serving paths, from SDK to network and infrastructure. You will lead incident response, design robust monitoring, and work with cross-team partners to ensure Claude’s reliability and performance.

The role emphasizes building scalable, high-availability systems with global reach and a strong emphasis on safety commitments and observability tooling.