Posted 23 Sept 2026
AI Red Team Tester
We're looking for AI Red Team Testers to go head-to-head with cutting-edge AI models — probing, prodding, and stress-testing them to uncover weaknesses before they cause real-world harm.
Hiring companyAlignerr
About the role
What if your curiosity and creative thinking could make AI systems safer for millions of people?
This is your chance to play the role of adversary in one of the most important challenges in tech today: making AI trustworthy. If you love puzzles, think laterally, and enjoy finding the cracks in systems that seem solid, this role was built for you.
Fully remote. Flexible hours. No security or hacking background required.
Why Join Us
- Work on genuinely important AI safety projects alongside leading research labs.
- Fully remote and flexible — structure your work around your life.
- Freelance autonomy with the satisfaction of meaningful, mission-driven work.
- Contribute directly to the responsible development of AI that impacts the world.
- Potential for ongoing work and contract extension as new projects launch.
Responsibilities
- Design imaginative prompts, scenarios, and conversation flows designed to trip up AI models.
- Attempt to coax AI systems into producing incorrect, biased, unsafe, or inappropriate outputs.
- Document every failure mode you discover with clear, reproducible steps.
- Assess and rate the severity and potential impact of identified issues.
- Collaborate asynchronously with AI safety and research teams to communicate your findings.
- Continuously develop new attack strategies as AI systems evolve.
Required skills
- A naturally curious, creative thinker who enjoys finding loopholes and solving puzzles.
- Comfortable adopting an adversarial mindset — thinking like someone trying to break the rules.
- Detail-oriented and methodical: you document what you find thoroughly and clearly.
- Strong written communicator who can explain issues in a structured, actionable way.
- Self-motivated and able to work independently on an async schedule.
Preferred skills
- Experience in creative writing, debate, philosophy, journalism, or research.
- Prior exposure to AI tools, chatbots, or language models as an end user.
- Background in ethics, psychology, or critical analysis.
- Familiarity with AI safety concepts or previous red teaming work.
Experience and education
- No hacking, cybersecurity, or AI background required — if you think creatively and communicate well, you're a strong candidate.
Schedule details
10–40 hours per week.
Eligibility
Work arrangement: Fully remote
Eligible countries: Mexico
Compensation details
$40–$120 per hour.
More about the hiring companyAlignerr
