Staff Software Engineer, AI Reliability Engineering
London, UK
Posted 16d ago
Remote Work Policy
On-site
Categories
Applied AI Engineer
About the job
AI Reliability Engineering (AIRE) partners with teams across Anthropic to improve reliability across our most critical serving paths, from SDKs through our network, API layers, serving infrastructure, and accelerators. This role involves jumping into the trenches alongside partner teams to make the systems that deliver Claude more robust and resilient, whether during an incident or collaborating on projects. Reliability is viewed as an emergent phenomenon that transcends single team boundaries, requiring a holistic perspective across the entire system.
Responsibilities
- Develop Service Level Objectives for large language model serving systems, balancing availability, latency, and 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, crucial for site reliability and Anthropic's safety commitments.
Requirements
- Strong distributed systems, infrastructure, or reliability backgrounds.
- Curiosity and bravery, with comfort in unfamiliar systems during incidents.
- Holistic thinking about system composition and seams.
- Ability to build lasting cross-team relationships.
- Ownership over outcomes, even for systems not directly managed.
- Excellent communication and collaboration skills.
- Diverse experience in areas like product stacks, database scaling, or large distributed systems.
Benefits
- Annual compensation range: £325,000 — £390,000 GBP
- Visa sponsorship available for some roles.