Join an elite AI Red Team to protect enterprise-scale AI products from threats. This hands-on role focuses on adversarial testing, ensuring operational impact in security measures.
You will lead testing efforts for LLM and various AI systems while designing threat models at multiple layers. Engage directly in executing red team scenarios such as prompt injection and model exploitation, translating your findings into structured documentation that aligns with enterprise governance frameworks.
Key Responsibilities:
• Design adversarial tests for AI systems and LLMs
• Conduct in-depth threat modeling for AI architectures
• Execute red team scenarios like data extraction and jailbreaking
• Collaborate with engineering and security teams effectively
• Present clear findings to executive leadership
Requirements:
• Strong understanding of adversarial machine learning
• Experience red-teaming LLM or AI systems
• Proven ability to map findings to security control...