AI Red Team Engineer

White Circle is seeking an AI Red Team Engineer to responsibly break LLM-powered systems, automate adversarial attacks, and generate clear evidence for customer demos and security reviews. The role involves owning end-to-end testing of chatbots, RAG pipelines, and AI agents to identify vulnerabilities like prompt injection and policy bypass. You will script attacks in Python, build internal test libraries, and convert findings into actionable product requirements to ensure AI safety.