About the Role
Identity is at the heart of modern enterprise security — and when it breaks, the consequences are severe. We're looking for IAM professionals who deeply understand how identity systems fail in the real world to help train and evaluate cutting-edge AI models being developed by leading AI research labs.
Your expertise in access control, privilege escalation, and zero-trust architecture will directly shape how AI reasons about enterprise security risk. This is a unique opportunity to apply your security knowledge at the frontier of AI development.
- Organization: Alignerr
- Type: Hourly Contract
- Location: Fully Remote
- Commitment: 10–40 hours/week
What You'll Do
- Analyze realistic IAM, SSO, and access control scenarios to identify weaknesses, misconfigurations, and attack paths
- Classify permission issues, privilege escalation vectors, and identity-related security failures
- Review zero-trust models and evaluate access design decisions for correctness and risk
- Generate and validate realistic identity security scenarios used to train and benchmark AI systems
- Provide structured, expert-level feedback that helps AI learn how IAM risk actually emerges and propagates
Who You Are
- 2+ years of hands-on experience with IAM, SSO, or enterprise identity platforms (e.g., Okta, Azure AD, Ping, CyberArk)
- Solid understanding of RBAC, least-privilege principles, and access review processes
- Familiar with how identity failures occur in practice and how attackers exploit them
- Able to think analytically and communicate security concepts clearly in writing
- Self-directed and comfortable working independently on task-based assignments
Nice to Have
- Experience with cloud identity platforms (AWS IAM, GCP IAM, Azure RBAC)
- Background in penetration testing, red teaming, or security architecture
- Familiarity with compliance frameworks like SOC 2, ISO 27001, or NIST
- Prior experience contributing to AI training or data annotation projects
Why Join Us
- Work directly on frontier AI systems alongside world-class research teams
- Fully remote and flexible — set your own hours and work at your own pace
- Freelance autonomy with meaningful, intellectually engaging work
- Contribute to AI that better understands real-world cybersecurity challenges
- Potential for ongoing work and contract extension based on performance