About The Role

What if your security expertise could directly shape how the world's most powerful AI systems defend themselves against attack? We're looking for AI Security Analysts to work alongside leading AI research teams — probing frontier models for vulnerabilities, analyzing adversarial behavior, and helping ensure that cutting-edge AI remains safe, reliable, and resistant to misuse.

This is a fully remote, flexible contract role built for security professionals who are genuinely curious about how modern AI systems are built, deployed, and exploited.

Organization: Alignerr Type: Hourly Contract Location: Remote Commitment: 10–40 hours/week

What You'll Do

Analyze AI and LLM security scenarios to understand how models behave under adversarial or unexpected conditions Review and evaluate cases involving prompt injection, data leakage, model abuse, and system misuse Classify security issues and recommend appropriate mitigations based on real-world impact and likelihood Assess AI system behavior against security best practices and help identify gaps Work across realistic, hands-on scenarios that reflect the actual threat landscape facing modern AI deployments Complete task-based assignments independently on your own schedule

Who You Are

Solid background in cybersecurity — offensive, defensive, or research-focused Genuine curiosity about how AI systems are built, trained, and deployed in real-world environments Strong understanding of modern threat modeling and how it applies to emerging AI technologies Analytical and precise — you think in edge cases and enjoy pulling apart complex systems Comfortable working independently and communicating findings clearly in writing No formal AI research background required — security instincts and curiosity are what matter

Nice to Have

Experience with LLM security, red-teaming AI systems, or adversarial ML research Familiarity with prompt injection techniques, jailbreaking, or model abuse vectors Background in application security, penetration testing, or vulnerability research Prior exposure to AI safety or alignment concepts Experience writing security assessments, threat models, or technical risk reports

Why Join Us

Work directly on frontier AI systems alongside world-class research labs Fully remote and flexible — work when and where it suits you Freelance autonomy with the structure of meaningful, impactful work Contribute to AI security at a critical moment in the development of the technology Potential for ongoing work and contract extension as new projects launch