AI Red Team Tester

Alignerr Corp.; Portugal; À distance; EUR 41 000 - 83 000; Temps partiel

Avantages offerts par ce poste

Fully remote

Flexible schedule

Contract extension potential

Résumé du poste

Alignerr is seeking AI Red Team Testers for remote, hourly contract work. You will design prompts and scenarios to probe AI models, aim to elicit unsafe outputs, and document findings with clear steps. Requires strong written English and analytical mindset.

Enjoy freelance autonomy with flexible hours and the possibility of ongoing projects or extensions as new work launches. No prior AI or cybersecurity background required.

Qualifications

Responsabilités

• Design prompts, scenarios, and flows to probe AI model weaknesses.
• Attempt to elicit unsafe or biased outputs from AI systems.
• Document failures with clear, reproducible steps.
• Rate severity and impact of issues.
• Provide structured feedback using rubrics.
• Collaborate asynchronously with safety and research teams.

Description du poste

About The Role

What if your curiosity and creative thinking could make AI safer for millions of people? We're looking for AI Red Team Testers to do something genuinely unique: try to break AI systems on purpose.

About The Role

What if your curiosity and creative thinking could make AI safer for millions of people? We're looking for AI Red Team Testers to do something genuinely unique: try to break AI systems on purpose.

• Organization: Alignerr
• Type: Hourly Contract
• Location: Remote
• Commitment: 10–40 hours/week

What You'll Do

• Design creative prompts, scenarios, and conversation flows to probe AI model weaknesses
• Attempt to elicit incorrect, unsafe, biased, or policy-violating outputs from AI systems
• Document every failure mode you discover with clear, reproducible steps
• Rate the severity and potential impact of identified issues
• Provide structured, detailed feedback using evaluation tools and rubrics
• Collaborate asynchronously with AI safety and research teams
• Work independently on your own schedule across varied and intellectually stimulating tasks

Who You Are

• Naturally curious — you enjoy thinking around corners and finding unexpected solutions
• Comfortable with adversarial thinking and pushing systems to their limits
• Detail-oriented and systematic — you document findings clearly and thoroughly
• Strong written communication skills in English
• Able to assess and articulate the severity and context of issues you discover
• No prior AI, cybersecurity, or technical background required

Nice to Have

• Experience in writing, journalism, research, or critical analysis
• Familiarity with AI tools or large language models as an end user
• Background in ethics, philosophy, psychology, or social science
• Prior experience in quality assurance, testing, or evaluation roles

Why Join Us

• Work on real AI safety projects alongside leading research labs and top AI teams
• Fully remote and flexible — work when and where it suits you
• Freelance autonomy with meaningful, intellectually engaging task-based work
• Contribute directly to making AI systems safer and more reliable for everyone
• Variety in every session — no two testing scenarios are the same
• Potential for ongoing work and contract extension as new projects launch