What if your security expertise could directly shape how the world's most advanced AI systems defend themselves against attack? We're looking for AI Security Analysts to probe, stress-test, and evaluate frontier AI models — uncovering vulnerabilities before they become real-world problems.
This is a fully remote, versátil contract role for security professionals who are curious about AI and want to work on the cutting edge of where cybersecurity meets machine learning. If you think in threat models, love finding what breaks, and want your work to matter at scale — this is the role for you.
Analyze real-world AI and LLM security scenarios to understand how models behave under adversarial or unexpected conditions
Investigate and evaluate prompt injection, data leakage, model abuse, jailbreaking, and system misuse cases
Classify security issues by real-world impact and likelihood,
and recommend appropriate mitigations
Help evaluate and improve AI system behavior so it remains safe, reliable, and aligned with security best practices
Work independently and asynchronously on task-based assignments — fully on your own schedule
Who You Are
Background in cybersecurity, information security, or a closely related technical field
Solid understanding of modern threat modeling principles applied to software systems
Familiar with how AI and LLM systems are built, deployed, and potentially exploited
Analytically sharp and precise — you think in edge cases and don't miss details
Naturally curious about emerging technologies and how they can be pushed, broken, or misused
Self-motivated and reliable when working independently without hand-holding
Nice to Have
Hands-on experience with penetration testing, red teaming, or vulnerability research
Familiarity with prompt injection, adversarial prompting, or AI-s