Become a key player in AI security with our elite Red Team specializing in adversarial testing. This role requires practical experience to design and execute red team engagements across AI systems.
We are seeking a Security Engineer to enhance the robustness of enterprise-scale AI products. Your responsibilities will include designing adversarial testing protocols and threat modeling for model and infrastructure layers. You’ll work closely with teams across engineering and compliance to ensure security findings lead to operational improvements.
Key Responsibilities:
• Design adversarial testing for LLM and AI-driven systems
• Conduct comprehensive threat modeling for AI architectures
• Execute testing for prompt injection, jailbreaking, and model exploitation
• Create structured audit-ready documentation for findings
• Present security findings to executive leadership and key stakeholders
Requirements:
• Strong background in adversarial machine learning
• ...