The engineer tunes and operates inference-time guardrails, tests AI systems for issues such as prompt injection, sensitive data exposure, excessive permissions, and unsafe agent actions, builds visibility into AI usage and agent activity, and integrates AI security tooling with Lilly's cloud, endpoint, identity, and security operations platforms. Our current groups include: Africa, Middle East, Central Asia (AMECA), Black Employees at Lilly (BE@Lilly), Chinese Culture Network (CCN), EnAble, Evolve, Lilly Indian Network (LIN), Organization of Latinx at Lilly (OLA), Pride (LGBTQ+ Allies), Veterans Leadership Network (VLN) and Women's Initiative for Leading at Lilly (WILL).