We are looking for a Performance QA Engineer to specialize in benchmarking and optimizing our Agentic AI platform. You will be the gatekeeper of the User Experience of Thought, ensuring that as our AI agents plan, reason, and execute tasks, they do so within acceptable timeframes and cost-efficiency boundaries.

Your mission is to stress-test the entire AI pipeline—from the initial prompt to the final autonomous action—identifying bottlenecks in LLM response times, RAG (Retrieval-Augmented Generation) retrieval speeds, and third-party API orchestration.

Key Responsibilities