Posted 18 Sept 2026
AI Security Tester
We're looking for security-minded professionals to help stress-test and harden AI systems by finding vulnerabilities before bad actors do.
Hiring companyAlignerr
About the role
If you've ever looked at a system and instinctively started thinking about how to break it, this role was made for you.
You'll conduct red-team exercises, craft adversarial prompts, and deliver expert feedback that directly shapes the safety and reliability of AI products used by millions of people worldwide.
Why Join Us
- Work at the frontier of AI security alongside top research labs.
- Directly influence the safety and robustness of AI systems at scale.
- Full autonomy and a flexible schedule — work when and how you want.
- Build highly sought-after expertise in one of the fastest-growing fields in tech.
- Potential for ongoing work, expanded scope, and long-term contract extension.
- Be part of a global, collaborative community of experts shaping the future of AI.
Responsibilities
- Conduct red-teaming exercises to identify security weaknesses and failure modes in AI systems.
- Craft adversarial prompts and edge-case scenarios designed to probe and stress-test model guardrails.
- Evaluate AI outputs for safety risks, bias, and policy compliance.
- 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.
Required skills
- You have a solid understanding of cybersecurity concepts, threat modeling, or penetration testing.
- You're a creative, analytical thinker who enjoys finding cracks in complex systems.
- You write clearly and document findings in an organized, structured way.
- You're comfortable working independently on task-based, asynchronous assignments.
Preferred skills
- Familiarity with open-source AI platforms is a plus.
- A background in infosec, ethical hacking, or AI safety research is a bonus — but not required.
Experience and education
- You've worked hands-on with AI/ML systems, large language models, or prompt engineering.
Schedule details
10–40 hours per week.
Eligibility
Work arrangement: Fully remote
Eligible countries: United States
Eligible regions: New York
Compensation details
$15–$75 per hour.
More about the hiring companyAlignerr
