AI Security & Risk Analyst
- Hiring Organisation
- The Citation Group
- Location
- Wilmslow, England, United Kingdom
treatment, working with relevant teams to design and implement controls. LLM & Agentic Security Assess the specific risks introduced by large language models and agentic AI systems, including prompt injection, jailbreaking, indirect prompt injection via external data sources, and unintended tool invocation. Evaluate agentic workflows for excessive permissions, insufficient … Able to identify and articulate risks that requesters have not considered. AI & Agentic Systems Knowledge: A working understanding of how LLMs, agentic AI, MCP servers, and AI integration patterns function, and the security risks they introduce, including prompt injection, tool misuse, data leakage, permissions ...