About The Position

This role is for one of the client’s extended-workforce opportunities at a leading AI lab. The specialist will contribute to the development and evaluation of next-generation foundational AI models, bringing an adversarial, security-focused, and safety-first perspective. The work involves identifying vulnerabilities and potentially harmful model behaviour, designing realistic adversarial scenarios, and establishing evaluation standards to improve the security, reliability, and responsible use of AI systems. The position is a W-2 employment opportunity. Compensation is $90–$140 per hour.

Requirements

  • At least 4 years of professional experience in Cybersecurity, Application Security, Red Teaming, Penetration Testing, Threat Intelligence, Incident Response, or Trust and Safety.
  • Hands-on expertise in at least one of the following: application security; offensive security and penetration testing; threat intelligence and incident response; or trust and safety.
  • Strong understanding of cybersecurity principles, common attack vectors, vulnerability management, and security best practices.
  • Practical experience identifying and evaluating security vulnerabilities across applications, systems, infrastructure, or AI-powered environments.
  • Ability to design adversarial scenarios and evaluate AI-generated responses for security weaknesses, unsafe behaviour, and potential misuse.
  • Demonstrable career progression, with increasing responsibility in security engineering, offensive security, threat analysis, or trust and safety functions.
  • Strong analytical and problem-solving abilities, including the capacity to investigate complex security issues and communicate findings effectively.
  • Ability to commit reliably to at least 20 hours per week during weekdays.
  • Excellent written communication skills, including the ability to explain technical concepts, security findings, risk assessments, and evaluation decisions clearly.

Nice To Haves

  • Experience at a recognised technology company, cybersecurity organisation, or established enterprise.
  • Familiarity with AI safety and Responsible AI concepts, including model security, adversarial robustness, harmful-output prevention, privacy risks, bias, and policy compliance.
  • Relevant industry certifications such as OSCP, OSWE, GPEN, or CISSP.
  • Published CVEs, recognised bug bounty findings, security research, technical publications, or meaningful contributions to cybersecurity projects.

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 challenging, domain-specific tasks based on real-world security and AI safety scenarios, and develop accurate, 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 threats including prompt injection, data leakage, insecure code generation, harmful instructions, and other relevant attack patterns.
  • Develop evaluation frameworks, scoring rubrics, and quality standards to assess the safety, reliability, accuracy, and potential harm of AI-generated responses, particularly on security-sensitive topics.
  • Identify weaknesses in AI model responses and provide clear, structured, actionable technical feedback to support improvements.
  • Apply relevant cybersecurity and trust and safety methodologies to evaluate model behaviour across threat scenarios and sensitive use cases.
  • Work with other subject matter experts to maintain consistency, accuracy, and quality across AI training datasets.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service