Staff Software Engineer, AI Reliability

Overview

Staff Software Engineer, AI Reliability within AIRE (AI Reliability Engineering) to improve reliability across critical LLM serving paths, from SDK through network/API layers and infrastructure.

What you'll do

• Develop Service Level Objectives for large language model serving systems balancing availability, latency, and development velocity.
• Design and implement monitoring and observability systems across the token path.
• Help design and implement high-availability serving infrastructure across multiple regions and cloud provider(s).
• Lead incident response for critical AI services, including recovery, incident reviews, and systematic improvements.
• Support safeguard model serving for reliability and safety-related commitments.

What you'll need

• Strong distributed systems, infrastructure, or reliability background.
• Comfort jumping into unfamiliar systems during incidents to help drive resolution.
• Ability to think holistically about how systems compose and where seams exist.
• Ability to build lasting relationships across teams as an embedded teammate.
• Excellent communication and collaboration skills.
• Care about users and feel ownership over outcomes for systems you don't directly own.

Details

• Location-based hybrid policy: expected to be in one of the offices at least 25% of the time.
• Visa sponsorship: available, with efforts to sponsor if an offer is made.