AI Safety, Responsible AI & Cybersecurity Specialist (AI Evaluation)
W
Weekday AIAI cybersecurity
United StatesPart-TimeMiddle
Salary90 - 140 USD per hour
Apply NowOpens the employer's application page
Job Details
- Experience
- 4+ years of professional experience
- Required Skills
- Cybersecurity
Requirements
- Have 4+ years of professional experience in cybersecurity, application security, red teaming, penetration testing, threat intelligence, incident response, or trust and safety.
- Bring hands-on expertise in at least one relevant area, such as secure code reviews, vulnerability assessments, application security testing, or security architecture.
- Alternatively, bring offensive security experience in vulnerability discovery, exploitation, penetration testing, adversarial testing, or security assessments.
- Alternatively, bring threat intelligence or incident response experience, including threat analysis, attack investigation, security monitoring, incident handling, threat modelling, or risk assessment.
- Alternatively, bring trust and safety experience in content moderation, platform abuse prevention, policy enforcement, harmful content identification, safety evaluations, or risk mitigation.
- Have a strong understanding of cybersecurity principles, common attack vectors, vulnerability management, and security best practices.
- Have practical experience identifying and evaluating vulnerabilities across applications, systems, infrastructure, or AI-powered environments.
- Be able to design adversarial scenarios and evaluate AI-generated responses for security weaknesses, unsafe behaviour, and potential misuse.
- Be able to commit reliably to at least 20 hours per week during weekdays.
- Relevant certifications such as OSCP, OSWE, GPEN, or CISSP are advantageous.
- Published CVEs, recognised bug bounty findings, security research, technical publications, or meaningful cybersecurity project contributions are strong advantages.
Responsibilities
- Collaborate with research and engineering teams to identify knowledge gaps and improve AI model performance across cybersecurity, Responsible AI, application and infrastructure security, red teaming, and abuse prevention.
- Design domain-specific tasks based on real-world security and AI safety scenarios, with accurate and well-structured solutions.
- Evaluate AI-generated security and Responsible AI outputs for technical accuracy, safety, policy compliance, and potential misuse.
- Create adversarial prompts, security challenges, and red teaming scenarios to test AI systems for vulnerabilities, unsafe responses, harmful behaviour, and policy violations.
- Assess AI systems for prompt injection, data leakage, insecure code generation, harmful instructions, and other attack patterns.
- Develop evaluation frameworks, scoring rubrics, and quality standards for safety, reliability, accuracy, and potential harm.
- Identify weaknesses in AI model responses and provide clear, structured, actionable technical feedback.
- Apply cybersecurity and trust and safety methodologies to evaluate model behaviour across threat scenarios and sensitive use cases.
- Work with subject matter experts to maintain consistency, accuracy, and quality across AI training datasets.
View Full Description & ApplyYou'll be redirected to the employer's site