Job Description
Lexsi Labs is a frontier AI lab focused on building aligned, interpretable, and safe superintelligent systems . Our work spans alignment methodologies, interpretability-led system design, and foundational model research across structured, tabular, and enterprise data. We build AI systems intended for real-world deployment, where transparency, auditability, and robustness are first-class constraints.
We operate with a flat structure, high autonomy, and a strong bias toward engineers who take full ownership of what they build, from architecture to production behavior.
The Role
We are building a high-autonomy AI Engineering Agent that can execute end-to-end AI engineering workflows on top of the Lexsi backend. The system is designed to reason over complex objectives, plan multi-step actions, interact with tools and data systems, evaluate outcomes, and iterate over long horizons while r...