Responsible AI / Security Specialist

• Guide research and engineering teams to close knowledge gaps and improve AI model performance in security and responsible AI, application and infrastructure security, and red teaming and abuse prevention topics.
• Design challenging, domain-relevant tasks, and write accurate and well-structured solutions to security and responsible AI problems.
• Evaluate security and responsible AI tasks and solutions and provide clear, written technical feedback.
• Design adversarial tasks and red teaming scenarios that probe AI systems for security vulnerabilities, unsafe behavior and policy violations.
• Develop rubrics to assess the safety, accuracy and harm potential of AI responses on security and sensitive topics.
• Collaborate with other subject matter experts to ensure consistency and accuracy in training data.

• 4+ years of dedicated professional experience in cybersecurity, red teaming, penetration testing, threat intelligence or trust and safety at a recognized, top-tier organization.
• Hands-on experience in at least one of: application security and secure code review, penetration testing and offensive security, threat intelligence or incident response, or trust and safety policy enforcement.
• Ability to engage reliably for at least 20 hours/week during weekdays.
• Strong written communication skills and the ability to explain complex technical decisions clearly.

• Relevant credentials such as OSCP, OSWE, GPEN, CISSP or published CVEs, bug bounty findings or security research.
• Demonstrable career progression.

Project and contracting process: the hiring partner. Applications continue on the provider's website.