Design and develop a Cursor-like chat to help operators and engineers quickly build and iterate on our DSL. Build robust self-healing mechanisms for broken automation steps and expand support for more advanced AI-driven actions. Increase observability of our LLM usage to reduce latency, cost, and token consumption. Develop evaluation frameworks to rigorously assess and improve prompt quality, model performance, and output reliability. Partner directly with the founders to prioritize roadmap, scope projects, and ship iteratively. The ideal candidate should have strong software engineering skills, experience with frontend development, and familiarity with LLM-driven products.