About the Role
What if your curiosity, creativity, and knack for thinking outside the box could directly make AI safer for millions of people? We're looking for AI Red Team Testers to put cutting-edge AI systems to the ultimate test — crafting clever prompts, probing for blind spots, and uncovering the failure modes that researchers need to fix.
This is your chance to do work that genuinely matters. No security background. No hacking experience. Just sharp thinking and a drive to find what others miss.
- Organization: Alignerr
- Type: Hourly Contract
- Location: Remote
- Commitment: 10–40 hours/week
What You'll Do
- Design creative, adversarial prompts and scenarios to expose weaknesses in AI models
- Attempt to elicit incorrect, unsafe, biased, or inappropriate outputs from AI systems
- Document every failure mode you discover with clear, reproducible steps
- Rate and classify the severity of issues using structured evaluation frameworks
- Collaborate asynchronously with AI safety and research teams to share findings
- Explore edge cases, unusual inputs, and unexpected use cases that stress-test model behavior
Who You Are
- A naturally curious, creative thinker who enjoys puzzles and lateral thinking
- Comfortable adopting an adversarial mindset — you like finding what's broken
- Strong written communication skills — you can clearly explain what you found and how to reproduce it
- Systematic and detail-oriented — you document findings thoroughly and consistently
- Self-motivated and reliable when working independently and asynchronously
- No hacking, cybersecurity, or technical AI background required
Nice to Have
- Experience in writing, creative fiction, journalism, or persuasive communication
- Background in philosophy, ethics, psychology, or social science
- Familiarity with AI chatbots or language models as an end user
- Prior experience in quality assurance, testing, or critical analysis
Why Join Us
- Work at the frontier of AI safety alongside leading research labs
- Fully remote and flexible — work on your own schedule, anywhere in the world
- Freelance autonomy with meaningful, intellectually stimulating task-based work
- Contribute to AI development that has a real and lasting impact on how safely AI operates in the world
- Potential for ongoing work and contract extension as new projects launch