Staff Software Engineer, AI Reliability Engineering

Anthropic's AI Reliability Engineering (AIRE) team partners with teams across the company to improve reliability across critical serving paths, from SDK through network, API layers, serving infrastructure, and accelerators. The team works on systems that deliver Claude, ensuring robustness and resilience during incidents and projects.

• 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 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 reliability of safeguard model serving.

Strong distributed systems, infrastructure, or reliability backgrounds; curiosity and comfort in unfamiliar systems; holistic thinking; ability to build cross-team relationships; ownership over outcomes; excellent communication; diverse experience. Strong candidates may have SRE/Production Engineer experience, experience operating large-scale model serving or training infrastructure (>1000 GPUs), experience with ML hardware accelerators (GPUs, TPUs, Trainium), ML-specific networking (RDMA, InfiniBand), AI-specific observability tools, chaos engineering, and open-source contributions.

Annual Salary: £325,000—£390,000 GBP.

Anthropic offers competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space.

Apply via the Greenhouse job posting. Anthropic encourages applications even if you don't meet every qualification.