White Circle is seeking a research scientist to study how LLM agents fail in the wild, elicit deception, misalignment, and unsafe behaviour in concrete experiments, and build out the understanding of how agents break or misbehave in realistic and user‑related scenarios.
You will own research projects end to end—from unclear concerns to falsifiable experiments and defensive baselines—and develop automated audit agents that discover suspect model behaviour at scale.
#J-18808-Ljbffr…
