Senior AI Security Engineer (Red & Blue Team)

St. Fox Consultancy (SFC) is launching a specialized Security in AI practice. We are moving beyond traditional cybersecurity to secure the next generation of Agentic AI, LLMs, and Autonomous Systems. We are looking for a hybrid Security Engineer who refuses to pick a side. You are a Red Teamer who can craft sophisticated jailbreaks and prompt injections, but you are also a Blue Teamer who knows how to architect the guardrails to stop them. As a Forward Deployed Engineer (FDE), you will not just write reports from a desk. You will embed with our enterprise clients, attacking their live AI agents to find vulnerabilities and then working side-by-side with their engineering teams to implement the fixes. Key Responsibilities: The Red (Adversarial Simulation) AI Red Teaming: Conduct advanced adversarial testing on Large Language Models (LLMs) and Agentic AI workflows. Execute prompt injections, jailbreaking, model inversion, and data poisoning attacks. Agentic Threat Simulation: Test auton...