About the Role
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 stress-test frontier AI models — probing for weaknesses, analyzing real-world threat scenarios, and helping ensure the AI systems increasingly embedded in our world are safe, reliable, and resilient.
This is a fully remote, flexible contract role built for security professionals who are curious about how AI systems are built, deployed, and abused. If you've ever wondered what happens when you push a language model past its limits — this is the role for you.
- Organization: Alignerr
- Type: Hourly Contract
- Location: Remote
- Commitment: 10–40 hours/week
What You'll Do
- Analyze real-world AI and LLM security scenarios to understand how models behave under adversarial or unexpected conditions
- Investigate prompt injection attacks, data leakage risks, model abuse cases, and system misuse patterns
- Classify security vulnerabilities and evaluate appropriate mitigations based on real-world impact and likelihood
- Apply structured threat modeling frameworks to emerging AI technologies
- Evaluate and improve AI system behavior to ensure it remains safe, aligned, and resistant to exploitation
- Work independently and asynchronously — fully on your own schedule
Who You Are
- Background in cybersecurity, information security, or a closely related technical field
- Strong understanding of security threat modeling and how it applies to modern AI and LLM systems
- Familiar with adversarial attack surfaces — prompt injection, data exfiltration, privilege escalation, and system boundary abuse
- Analytical and precise — you think in edge cases and worst-case scenarios
- Naturally curious about how AI systems are built, and where they can break
- Comfortable working independently on complex, open-ended security problems
Nice to Have
- Hands-on experience with penetration testing, red teaming, or vulnerability research
- Familiarity with large language models, generative AI, or AI safety concepts
- Background in applied security research, DevSecOps, or secure software development
- Experience evaluating AI tools or APIs from a security perspective
Why Join Us
- Work directly on frontier AI systems alongside world-leading research labs
- Fully remote and flexible — work when and where it suits you
- Freelance autonomy with the structure of meaningful, high-impact security work
- Contribute to AI safety at the frontier — your analysis shapes how the most advanced models in the world defend against real threats
- Potential for ongoing work and contract extension as new projects launch