DevOps & Site Reliability Engineer

Role overview The available description centers on the runtime behind AI agents, including planning, tool use, memory and recovery. The work includes improving task success and making agent behavior observable, interruptible and safe; it does not specify infrastructure, deployment or site reliability responsibilities.

Responsibilities - Design and build agent orchestration and tool-calling systems. - Improve task success rates with measurable evaluations. - Make agent behavior observable and interruptible. - Support safe behavior and recovery in tool-using systems.

Requirements - Production experience building LLM-powered applications or agents. - Strong backend engineering skills in TypeScript or Python. - Understanding of failure modes in tool-using models.