Research Scientist, Agentic Systems & AI Safety

White Circle is seeking a research scientist to build autonomous, large-scale environments that test LLM agents to failure and study how they break. You will conduct end-to-end experiments with external APIs and internal models, focusing on agent behaviours and failure modes to inform safety research and public writeups.

The role emphasizes building non-trivial agent ecosystems, with strong emphasis on engineering, experimentation, and rigorous analysis to advance AI safety in production-like