AI Red Team Specialist — LLM Security Testing

We're releasing a consumer-facing AI assistant in 8 weeks. Before we do, we want it red teamed properly. We need an AI red team specialist to systematically probe our system for: – Prompt injection vulnerabilities – Jailbreaks and policy violations – Hallucination patterns in high-risk domains – Data leakage risks – Adversarial robustness Deliverables: written report with severity ratings, reproduction scripts, and recommendations for mitigations. This is a security-focused ML role. We need someone with real experience finding failure modes in LLM systems — not just a general AI consultant.