Description
We're seeking a Staff Software Engineer to join our AI Reliability Engineering team. As a key member of our team, you will develop Service Level Objectives for large language model serving systems, design and implement monitoring and observability systems, and lead incident response for critical AI services.
You will work closely with teams across Anthropic to improve reliability across our most critical serving paths. You will be responsible for making the systems that deliver Claude more robust and resilient, whether during an incident or collaborating on projects.
To be successful in this role, you should have strong distributed systems, infrastructure, or reliability backgrounds. You should be curious and brave, comfortable jumping into unfamiliar systems during an incident and helping drive resolution even when you don't have deep expertise yet.
You will be working on high-availability serving infrastructure across multiple regions and cloud providers. You will support the reliability of safeguard model serving, which is critical for both site reliability and Anthropic's safety commitments.
If you're committed to creating reliable, interpretable, and steerable AI systems, and you're passionate about working on complex technical problems, we'd love to hear from you.