Skills & Expectations: Strong expertise in AI safety tools (e.g., Responsible AI Toolbox, Deepchecks) Experience with LLM compliance testing frameworks Hands-on knowledge in: Prompt injection testing and AI behaviour anomaly detection Bias, fairness, and explain ability metrics for LLMs Audit trail generation, logging, and compliance reporting (GDPR/DSAR) Security risk mitigation in AI agent systems

AMRT1_UKTJ ...