Global Red Team AI Engineer, AVP

What you’d do

Conduct adversarial testing of AI and LLM systems, including prompt injection, data leakage, and guardrail bypass scenarios, and document findings with risk impact and remediation. Full time role analyzing AI applications, agents, and APIs for security and abuse risks. Found on the employer's careers page on Oct 17, 2026. Apply through the link.

You’ll need

• 4+ years in offensive security, red team, or penetration testing
• Hands-on security assessment or adversary emulation experience
• AI/LLM adversarial testing skills
• Knowledge of prompt injection and guardrail bypass
• Vulnerability analysis and threat-informed testing