Quality Assurance & Test Automation Engineer

Role overview Build and improve the backend runtime that enables AI agents to plan tasks, use tools, retain memory and recover from failures. The work focuses on orchestration, measurable performance and making agent actions easier to monitor and control.

Responsibilities - Design and implement systems for coordinating agent tasks and tool calls. - Develop runtime capabilities for planning, memory and recovery. - Create evaluations that measure task success and guide improvements. - Make agent behavior observable, interruptible and safe. - Investigate failure patterns in tool-using models and address them in the system.

Requirements - Experience delivering LLM-powered applications or agents in production. - Strong backend engineering skills in TypeScript or Python. - Understanding of common failure modes in models that use tools.