AI Red Teamer

• Conduct penetration testing on AI systems to identify security vulnerabilities in predictive and generative models.
• Develop and execute adversarial attacks including poisoning, evasion, jailbreaking, and prompt injection.
• Collaborate with data scientists and engineering teams to design novel attacks and provide security recommendations.
• Produce detailed reports documenting vulnerabilities, risks, and mitigation strategies.

This role helps secure AI systems against malicious attacks, protecting organizations and society from potential harms of AI vulnerabilities.

• Experience in penetration testing or red teaming, preferably on AI/ML systems.
• Strong understanding of adversarial machine learning techniques (e.g., poisoning, evasion, jailbreaking).
• Proficiency in Python and familiarity with AI/ML frameworks.
• Ability to produce clear technical reports and communicate security risks.

Competitive compensation and benefits package. Specific details not provided.

HiddenLayer is a cybersecurity company focused on protecting AI and machine learning systems from adversarial threats.