
AI Safety, Responsible AI, Cybersecurity Specialist
Posted 3 days ago

Posted 3 days ago
This is a fully remote position, open to applicants in United States.
• Collaborate with research and engineering teams to pinpoint knowledge gaps and enhance AI model efficacy in areas such as cybersecurity, Responsible AI, application and infrastructure security, red teaming, and abuse prevention.
• Design specific tasks tailored to real-world security and AI safety scenarios, creating precise and well-organized solutions.
• Assess AI-generated security and Responsible AI outputs for technical precision, safety, adherence to policy, and risks of misuse.
• Develop adversarial prompts, security challenges, and red teaming scenarios to evaluate AI systems for vulnerabilities, unsafe responses, harmful behavior, and policy breaches.
• Evaluate AI systems against threats such as prompt injection, data leakage, insecure code generation, harmful instructions, and various attack patterns.
• Create evaluation frameworks, scoring rubrics, and quality standards for AI-generated outputs.
• Identify deficiencies in AI model responses and deliver structured, actionable technical feedback.
• Implement cybersecurity and trust and safety methodologies across diverse threat scenarios and sensitive applications.
• Collaborate with subject matter experts to ensure consistency, accuracy, and quality in AI training datasets.
• A minimum of 4 years of professional experience in Cybersecurity, Application Security, Red Teaming, Penetration Testing, Threat Intelligence, Incident Response, or Trust and Safety.
• Hands-on experience in at least one of the following areas: Application Security; Offensive Security & Penetration Testing; Threat Intelligence & Incident Response; Trust & Safety.
• A solid understanding of cybersecurity principles, common attack vectors, vulnerability management, and best security practices.
• Practical experience in identifying and assessing security vulnerabilities within applications, systems, infrastructure, or AI-powered environments.
• Familiarity with AI safety and Responsible AI principles, including model security, adversarial robustness, harmful-output prevention, privacy risks, bias, and policy compliance is highly desirable.
• Capability to design adversarial scenarios and assess AI-generated responses for security vulnerabilities, unsafe behavior, and potential misuse.
• Relevant industry certifications such as OSCP, OSWE, GPEN, or CISSP are advantageous.
• Published CVEs, acknowledged bug bounty contributions, security research, technical publications, or substantial contributions to cybersecurity initiatives are significant advantages.
• Proven career advancement with increasing responsibilities in security engineering, offensive security, threat analysis, or trust and safety roles.
• Strong analytical and problem-solving skills.
• Willingness to commit to at least 20 hours per week during weekdays.
• Excellent written communication abilities for clearly explaining complex technical concepts, security findings, risk assessments, and evaluation decisions.
• W-2 employment opportunity.
• Chance to be part of a leading AI lab’s extended workforce.
NetImpact Strategies Inc.
Vannevar Labs
GuidePoint Security
Checkly
Get handpicked remote jobs straight to your inbox weekly.