Summary

Staff software engineer in ai reliability engineering at anthropic, partnering across teams to improve reliability for large language model serving. You will develop service level objectives, build monitoring and observability for the token path, and help design high-availability infrastructure across regions and cloud providers. The role is hybrid, with staff expected to be in an office at least 25% of the time.

Responsibilities

• Develop service level objectives for llm serving
• Design monitoring and observability for token path
• Implement high-availability serving infrastructure
• Lead incident response for critical ai services
• Conduct incident reviews and drive improvements
• Support reliability of safeguard model serving