Staff + Sr. Software Engineer, AI Reliability
Core
Design and implement monitoring, observability, and high-availability serving infrastructure for large language model systems to ensure robustness and rapid incident recovery.
Role type
Staff/Senior IC SRE (LLM serving infrastructure)
Builds
Production-grade serving infrastructure and observability systems for Anthropic's AI models
Domain
AI/ML infrastructure, distributed systems, cloud computing
Deliverable
infrastructure
Required skills
distributed systems, infrastructure, reliability engineering, incident response, high-availability architecture, multi-region deployment, cloud provider expertise
Preferred skills
SRE/Production Engineer experience, large-scale model serving (>1000 GPUs), ML hardware accelerators (GPUs, TPUs, Trainium), ML networking (RDMA, InfiniBand), AI observability tools, chaos engineering, open-source infrastructure contributions
Technologies
RDMA, InfiniBand, GPUs, TPUs, Trainium
Responsibilities
Develop Service Level Objectives for LLM serving systems, design monitoring and observability systems across the token path, assist in implementing high-availability serving infrastructure, lead incident response for critical AI services, support reliability of safeguard model serving
Seniority
Staff/Senior, hands-on IC
