The role involves improving the reliability of critical serving paths for AI systems. Responsibilities include developing service level objectives for large language model serving systems while balancing availability and latency. The position requires designing and implementing monitoring and observability systems across the token path. The individual will assist in creating high-availability serving infrastructure across multiple regions and cloud providers. Additionally, the role entails leading incident response efforts to ensure rapid recovery and systematic improvements.

Candidates must possess a background in distributed systems, infrastructure, or reliability. The role requires strong communication and collaboration skills to build relationships across teams. A bachelor's degree or an equivalent combination of education, training, and experience in a relevant field is required. Applicants should demonstrate a holistic approach to system composition and a willingness to engage with unfamiliar systems during incidents.