What if your security instincts could directly shape how the world's most advanced AI systems defend themselves against misuse, manipulation, and attack? We're looking for AI Security Analysts to work hands-on with frontier AI models — probing their limits, identifying vulnerabilities, and helping ensure these systems remain safe, reliable, and aligned with real-world security standards.
This is a fully remote, adaptable contract role built for security professionals who are curious about AI and want to work at the cutting edge of one of the most consequential technology challenges of our time.
Analyze AI and LLM security scenarios to understand how models behave under adversarial, edge-case, or unexpected conditions
Review and evaluate cases involving prompt injection, data leakage, model abuse, and system misuse
Classify security vulnerabilities and recommend appropriate mitigations based on real-world impact and likelihood
Apply threat modeling frameworks to emerging AI technologies and deployment contexts
Help evaluate and improve AI system behavior so it remains safe, aligned, and resistant to exploitation
Work independently on task-based assignments — fully on your own schedule
Who You Are
Background in security — whether offensive, defensive, or applied research
Strong understanding of modern threat modeling and how it applies to AI systems and LLMs
Curious and analytical — you enjoy pulling systems apart to understand how they fail
Precise and methodical when assessing complex risks and their real-world implications
Comfortable working independently across ambiguous, novel problem spaces
Genuinely interested in how AI systems are built, deployed, and potentially exploited
Nice to Have
Hands-on experience with penetration testing, red teaming, or vulnerability research
Familiarity with LLM architectures, AI deployment pipelines, or