About The Role
If you love finding cracks in systems before the bad guys do, this role was built for you. We're looking for security-minded professionals to help stress-test and harden some of the most advanced AI models in the world. You'll probe for vulnerabilities, craft adversarial prompts, and deliver expert feedback that directly shapes the safety and reliability of AI systems used by millions.
Organization: Alignerr
Type: Hourly Contract
Location: Remote
Commitment: 10–40 hours/week
What You'll Do
Conduct red-teaming exercises to identify security weaknesses and exploitable behaviors in AI systems
Design and execute adversarial prompts and edge-case scenarios to stress-test model guardrails
Evaluate AI outputs for safety failures, bias, and policy violations
Document vulnerabilities, exploits, and unexpected behaviors in clear, structured reports
Collaborate with engineering teams to recommend practical mitigations and improvements
Stay current on emerging AI security threats, jailbreak techniques, and evolving best practices
Help define and refine security evaluation rubrics and testing protocols
Who You Are
You have a solid grasp of cybersecurity concepts — threat modeling, penetration testing, or ethical hacking
You've worked with AI/ML systems, LLMs, or prompt engineering in some capacity
You're a creative, analytical thinker who enjoys breaking things to make them better
You communicate clearly in writing and can document complex findings for technical audiences
You're self-directed and comfortable working independently on asynchronous, task-based assignments
Familiarity with open-source AI platforms is a plus
A background in infosec, ethical hacking, or AI safety research is a plus — but not required
Why This Role Stands Out
Work at the frontier — contribute to AI safety research alongside leading labs and engineering teams
Real impact — your findings directly influence how AI systems are built and deployed at scale
Full autonomy — set your own hours, work from anywhere, and own your schedule
Grow fast — build deep expertise in one of the hottest and most consequential domains in tech
Stay engaged — high-quality contributors are considered for ongoing work and expanded scope
No gatekeeping — security professionals from any background are encouraged to apply