GenAI Security Researcher

A global startup in the Trust & Safety domain, developing an automated SaaS product based on AI and advanced models with the goal of cleaning the internet from harmful content. This is a low latency system operating in real-time to identify and act against harmful activities online, thus preventing damage to users and organizations.

They have raised over $100 million and have large paying customers since their inception.

Located near a train station and the light rail. They work in a hybrid model, combining 3-4 work-from-home days.

Key Responsibilities:

• Simulated Cyber Attacks: Conduct sophisticated and comprehensive simulated attacks on generative AI models and their operating environments to uncover vulnerabilities.

• Vulnerability Assessment: Evaluate the security posture of AI models and infrastructure, identifying weaknesses and potential threats.

• Risk Analysis: Perform thorough risk analysis to determine the impact of identified vulnerabilities and prioritize mitigation efforts.

• Mitigation Strategies: Collaborate with development and security teams to develop effective strategies to mitigate identified risks and enhance model resilience.

• Security Protocols Development: Aid in the creation and refinement of security protocols and best practices for the development and deployment of generative AI models.

• Research and Innovation: 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.

• Documentation and Reporting: Maintain detailed documentation of all red team activities, findings, and recommendations. Prepare and present reports to senior management and relevant stakeholders.

• Training and Awareness: Provide guidance and training to technical and non-technical teams on security awareness and best practices related to generative AI.

Required Qualifications:

• Bachelor’s or master’s degree in computer science, Information Security, or a related field.

• 5 years of experience in offensive cyber security, particularly in web application and API security, vulnerability assessment, and ethical hacking.

• Strong understanding of AI technologies and their underlying architectures, especially generative models like GPT, DALL-E, etc.

• Knowledge on AI vulnerabilities and possible mitigation strategies

• Familiarity with security frameworks, compliance standards, and ethical guidelines in AI.

• Proficiency in programming and scripting languages relevant to AI and cybersecurity (e.g., Python, JavaScript).

• Excellent analytical, problem-solving, and communication skills.

• Certifications in offensive cybersecurity (e.g., OSWA, OSWE, OSCE3, SEC542, SEC522) are highly desirable.