Gen AI Researcher

We are looking for a Gen AI Researcher to join our company. You will play a critical role in enhancing the security and integrity of our cutting-edge AI technologies. Your primary responsibility will be to conduct analysis and testing of our generative AI systems, including but not limited to language models, image generation models, and any related infrastructure.

The goal is to identify vulnerabilities, assess risks, and provide actionable insights to fortify our AI models and guardrails against potential threats.

Responsibilities:

• Conduct sophisticated and comprehensive simulated attacks on generative AI models and their operating environments to uncover vulnerabilities.
• Evaluate the security posture of AI models and infrastructure, identifying weaknesses and potential threats.
• Perform thorough risk analysis to determine the impact of identified vulnerabilities and prioritize mitigation efforts.
• Collaborate with development and security teams to develop effective strategies to mitigate identified risks and enhance model resilience.
• Stay abreast of the latest trends and developments in AI security, ethical hacking, and cyber threats. Apply innovative testing methodologies to ensure cutting-edge security practices.
• Maintain detailed documentation of all red team activities, findings, and recommendations. Prepare and present reports to senior management and relevant stakeholders.

Requirements:

• 5+ years of experience in offensive cyber security, particularly in Cloud and API security.
• Proven record of AI vulnerabilities analysis
• Strong understanding of AI technologies and their underlying architectures, especially generative models and frameworks.
• Familiarity with agentic frameworks and agentic development experience
• Proficiency in python.
• Excellent analytical, problem-solving, and communication skills.
• Ability to work in a fast-paced, ever-changing environment.
• Advanced Certifications in offensive cybersecurity (e.g. OSWE, OSCE3, SEC542, SEC522) are highly desirable.