The Staff Software Engineer, AI Reliability Engineering role at Anthropic focuses on improving reliability across critical serving paths of Claude. Responsibilities include developing SLAs, designing monitoring systems, building high-availability infrastructure, leading incident response, and supporting safeguard model serving. The position is hybrid, based in Dublin, IE, with a competitive compensation range of €235,000 to €295,000, and offers benefits such as equity donation matching, generous vacation and parental leave, and flexible working hours.
Staff Software Engineer, AI Reliability Engineering at Anthropic
Hybrid - Dublin, IE
More jobs at AnthropicSalary
EUR 235,000 - 295,000
Requirements
Skills
- Bachelor’s degree or an equivalent combination of education, training, and/or experience
- Experience in distributed systems, infrastructure, or reliability
- Strong communication and collaboration skills
- Curiosity and bravery in unfamiliar systems
- Experience as an SRE, Production Engineer, or similar reliability-focused role on large scale systems
- Experience operating large-scale model serving or training infrastructure (>1000 GPUs)
- Experience with ML hardware accelerators (GPUs, TPUs, Trainium)
- Understanding of ML-specific networking optimizations like RDMA and InfiniBand
- Expertise in AI-specific observability tools and frameworks
- Experience with chaos engineering and systematic resilience testing
- Contributions to open-source infrastructure or ML tooling
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 providers
- 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
Technologies
Service Level ObjectivesMonitoring and observability systemsHigh-availability serving infrastructureIncident response toolsSafeguard model servingDistributed systemsInfrastructureSRE toolsML hardware accelerators (GPUs, TPUs, Trainium)RDMAInfiniBandAI-specific observability tools and frameworksChaos engineering toolsOpen-source infrastructure or ML tooling
See if your resume is ready for this job
See how our AI can optimize your resume and improve your chances for this role.