A
Senior AI Red Team Security Specialist
Sin especificarProyectoSecurity ResearchCybersecurity
Join a specialized security team conducting high-impact, project-based assessments of generative AI models, agentic frameworks, and related infrastructure. The role focuses on identifying vulnerabilities, assessing risk, and helping clients improve the resilience of their AI technologies.
Responsabilidades
- Conduct sophisticated simulated attacks against generative AI models and their operating environments.
- Assess the security posture of AI models and infrastructure and identify vulnerabilities and threats.
- Analyze the potential impact of vulnerabilities and prioritize mitigation efforts.
- Collaborate with development and security teams on risk mitigation and model resilience.
- Research developments in AI security, ethical hacking, and cyber threats.
- Apply innovative testing methodologies to emerging AI technologies.
- Document red-team activities, findings, and recommendations.
- Prepare and present reports to senior management and other stakeholders.
Requisitos
- Proven experience analyzing AI vulnerabilities.
- Strong understanding of AI technologies and underlying architectures, particularly generative models and agentic frameworks.
- At least five years of web penetration testing experience.
- Strong analytical, problem-solving, and communication skills.
- Ability to work effectively in a fast-paced, changing environment.
- Successful completion of a screening exam and background check.
Se valora
- Proficiency in Python or Node.js.
- Advanced offensive cybersecurity certifications such as OSWE, OSCE3, SEC542, or SEC522.
- Experience with agentic frameworks or agentic development.
- A bachelor’s or master’s degree in computer science, information security, or a related field.
- A track record of vulnerability disclosure, such as CVEs.