Staff Software Engineer, AI Reliability Engineering

Overview

Build and operate reliability systems to keep Anthropic’s Claude dependable across the LLM serving stack, from SDK through network and infrastructure through incident response.

What you'll do

• Develop service level objectives for large language model serving systems.
• Design and implement monitoring and observability across the token path.
• Support high-availability serving infrastructure across multiple regions and cloud providers.
• Lead incident response for critical AI services.
• Support reliability for safeguard model serving.

What you'll need

• Strong distributed systems, infrastructure, or reliability background.
• Ability to jump into unfamiliar systems during incidents.
• Ability to think holistically about how systems compose and where seams are.
• Excellent communication and collaboration skills.
• Experience operating large-scale model serving or training infrastructure (>1000 GPUs).
• Experience with one or more ML hardware accelerators (GPUs, TPUs, Trainium).
• Minimum education: Bachelor’s degree or equivalent combination of education/training/experience.

Details

• Annual compensation range: €235,000–€295,000 EUR.
• Work mode: location-based hybrid policy; staff expected in office at least 25% of the time.
• Visa sponsorship: visas are sponsored for some roles/candidates with reasonable efforts if an offer is made.