Research Scientist — AI Safety & Agent Behavior

White Circle is an AI Safety company building the safety, reliability, and optimization layer for AI systems. We design policies, test them at scale, and push the boundaries of how safety is implemented in real world applications.

We’re a small, focused team that ships research to production quickly and shares findings publicly to reduce the risks of deploying capable agents. This role studies how LLM agents fail in the wild, elicits deception, misalignment, and unsafe behaviour in concrete

#J-18808-Ljbffr…