Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. The AI Reliability Engineering (AIRE) team partners across the company to improve reliability across our most critical serving paths—from the SDK and network to API layers and serving infrastructure. The role involves developing service level objectives, designing and implementing monitoring and observability systems, building high‑availability infrastructure across regions and cloud providers, leading incident response for critical AI services, and supporting the reliability of safeguard model serving to meet our safety commitments.
Staff Software Engineer, AI Reliability Engineering at Anthropic
Hybrid - Dublin, Ireland
More jobs at AnthropicSalary
EUR 235,000 - 295,000
Requirements
Skills
- Strong distributed systems, infrastructure, or reliability background
- Curious and brave, comfortable tackling unfamiliar systems during incidents
- Holistic systems thinking
- Ability to build lasting relationships across teams
- Excellent communication and collaboration skills
- Diverse experience with product stacks, scaled databases, and distributed systems
- SRE, Production Engineer, or similar reliability-focused roles 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
- Experience with AI-specific observability tools and frameworks
- Experience with chaos engineering and systematic resilience testing
- Contributed to open-source infrastructure or ML tooling
- Bachelor’s degree or an equivalent combination of education, training, and/or experience
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
Large language model serving systemsMonitoring and observability toolsHigh-availability serving infrastructureCloud providersGPUs, TPUs, TrainiumRDMA and InfiniBandChaos engineering toolsAI-specific observability frameworks
See if your resume is ready for this job
See how our AI can optimize your resume and improve your chances for this role.