Added
21 minutes ago
Type
Full time
Salary
Salary not provided

Related skills

penetration testing red team ai tools ai security pyrit

📋 Description

  • Design and execute adversarial testing campaigns for AI systems (LLMs, multimodal, autonomous
  • Research attack vectors, prompt injections, jailbreaks, and AI vulnerabilities.
  • Evaluate and implement AI security testing tools to detect AI threats faster.
  • Conduct red team exercises simulating real-world deployment and edge cases.
  • Test AI models for bias, toxicity, misinformation, and harmful outputs across contexts.
  • Execute standardized security tests and strengthen AI threat posture.

🎯 Requirements

  • Minimum 5 years in penetration testing, red team ops, offensive cybersecurity, or AI red teaming.
  • Bachelor’s degree or higher in CS/IT/AI/Cybersecurity or equivalent experience.
  • Demonstrated experience in AI red teaming, offensive cyber operations.
  • Hands-on experience with AI/security testing tools (SPLX, Garak, TextAttack, PyRIT, Burp Suite
  • Strong knowledge of web technologies and Layer 7 protocols (HTTP, DNS, FTP).
  • Technical understanding of Generative AI architectures and related protocols.

🎁 Benefits

  • Fully remote opportunity within the United States.
  • Work at the intersection of cybersecurity, QA, and AI technologies.
  • Exposure to advanced AI models, adversarial testing methodologies, and AI security threats.
  • Collaborate with global security, engineering, and development teams.
  • Influence AI security practices, testing standards, and risk mitigation strategies.
  • Professional growth with hands-on work with modern AI security tools.
Share job

Meet JobCopilot: Your Personal AI Job Hunter

Automatically Apply to Engineering Jobs. Just set your preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.

Related Engineering Jobs

See more Engineering jobs →