Description
- Conduct comprehensive testing campaigns against AI models.
- Research and identify vulnerabilities and unintended behaviors.
- Introduce tools to detect and respond to AI-specific threats.
- Simulate real-world scenarios to probe for harmful outputs.
- Create datasets to evaluate model robustness.
- Collaborate with teams to document findings and recommend mitigations.
- Maintain documentation and reports on testing activities.
Key Responsibilities
- Design and execute adversarial testing campaigns.
- Research attack vectors and techniques.
- Evaluate and introduce security tools for AI threats.
- Conduct red team exercises to identify harmful outputs.
- Collaborate with teams to mitigate identified risks.
Qualifications
- Minimum 5 years of experience in penetration testing or red team operations.
- Degree in computer science, IT, AI, or cybersecurity, or equivalent experience.
- Background in AI red teaming or offensive cyber operations.
- Understanding of AI, machine learning, and networking.
- Excellent communication and stakeholder management skills.
Core Technologies
SPLX | Garak | TextAttack | PyRIT | Burp Suite | Metasploit | Nessus | Cobalt Strike | NMAP | sqlmap | Python | Ruby | Go | C | PowerShell | bash