AI Security Engineer - Red Team Focus

Empower AI security by leading red team engagements at the forefront of machine learning challenges. This practical role positions you uniquely within enterprise AI security framework.

You will spearhead adversarial testing across various AI systems and engage in threat modeling for comprehensive security analysis. Collaborating closely with teams, your work will directly influence the security governance of deployed AI products, transforming risk findings into actionable insights.

Key Responsibilities:

• Execute adversarial testing across AI and LLM systems

• Facilitate threat modeling for data and infrastructure

• Manage testing scenarios like model exploitation and RAG manipulation

• Document findings in compliance-ready formats

• Communicate results effectively to leadership

Requirements:

• Strong expertise in adversarial machine learning techniques

• Experience in red-teaming AI systems and platforms

• Ability to connect security risks to framework standards

• Proficient in written and verbal communications

• Self-sufficient under executive guidance

Shape the future of AI security by integrating your insights for maximum compliance.
#J-18808-Ljbffr