Staff Software Engineer, AI Reliability Engineering

Anthropic's AI Reliability Engineering (AIRE) team partners with teams across Anthropic to improve reliability across critical serving paths, from SDK through network, API layers, serving infrastructure, and accelerators. The team works on making Claude's delivery systems more robust and resilient, during incidents and through collaborative 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 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.

Strong distributed systems, infrastructure, or reliability backgrounds; reliability-minded software engineers and SREs. Curiosity and bravery in unfamiliar systems, holistic thinking about system composition, ability to build cross-team relationships, user ownership, excellent communication, and diverse experience. Strong candidates may have SRE or production engineering experience, experience with large-scale model serving or training infrastructure (>1000 GPUs), ML hardware accelerators (GPUs, TPUs, Trainium), ML-specific networking optimizations (RDMA, InfiniBand), AI-specific observability tools, chaos engineering, or open-source contributions.

Annual salary range: €235,000—€295,000 EUR.

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

Apply via the Greenhouse link. Anthropic sponsors visas and encourages applications from underrepresented groups.