AI Red Team Tester

Alignerr Corp.; Brasil; Remote; BRL 55,000 - 96,000; Part time

Job summary

Alignerr is seeking AI Red Team Testers to challenge cutting-edge AI systems. You will craft prompts and scenarios to uncover weaknesses, surface blind spots, and help shape models toward greater safety, honesty, and robustness.

This is a remote hourly contract with flexible hours (10–40 hours/week). You will document findings clearly and work with researchers to drive safe, responsible AI development.

Qualifications

• Must be naturally curious and enjoy poking at systems to find what breaks.
• Able to document findings clearly with thorough notes and reproduction steps.
• Excellent written communication to convey issues and their significance.

Responsibilities

• Design prompts, scenarios, and conversation flows to expose AI weaknesses.
• Attempt to elicit unsafe or biased outputs from AI models.
• Document failure modes with precise reproduction steps.
• Rate severity and potential impact of each issue.
• Provide actionable feedback for safety and research teams.
• Collaborate asynchronously with AI research teams.

Skills

Curiosity

Creative thinking

Adversarial mindset

Detail-oriented

Written communication

Job description

About The Role

What if your curiosity and creative thinking could make AI safer for everyone? We're looking for AI Red Team Testers to challenge cutting-edge AI systems in ways their creators haven't anticipated — probing for weaknesses, surfacing blind spots, and helping shape models that are more robust, honest, and safe.

About The Role

What if your curiosity and creative thinking could make AI safer for everyone? We're looking for AI Red Team Testers to challenge cutting-edge AI systems in ways their creators haven't anticipated — probing for weaknesses, surfacing blind spots, and helping shape models that are more robust, honest, and safe.

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

What You'll Do

• Design creative prompts, scenarios, and conversation flows specifically crafted to expose AI weaknesses
• Attempt to elicit incorrect, biased, unsafe, or otherwise problematic outputs from AI models
• Document discovered failure modes clearly, including precise reproduction steps
• Rate the severity and potential impact of each issue you uncover
• Provide structured, actionable feedback that safety and research teams can act on
• Collaborate asynchronously with researchers working on the frontier of AI development

Who You Are

• A naturally curious, creative thinker who enjoys poking at systems and finding what breaks
• Comfortable approaching problems adversarially — you think in edge cases and "what ifs"
• Detail-oriented and systematic: you document findings thoroughly, not just intuitively
• A clear, precise written communicator who can explain what you found and why it matters
• Self-directed and reliable — you can manage your own time and hit deadlines independently
• No cybersecurity, hacking, or technical background required

Nice to Have

• Experience with writing, journalism, research, philosophy, or logic-based disciplines
• Familiarity with AI tools, chatbots, or language models as an end user
• Background in ethics, psychology, or social sciences — useful for spotting bias and harmful patterns
• Prior experience in QA, testing, or structured evaluation workflows

Why Join Us

• Work on real, high-impact AI safety projects alongside leading research labs
• Fully remote and flexible — design your own schedule and work from anywhere
• Freelance autonomy with meaningful, intellectually stimulating task-based work
• Contribute to AI development that genuinely matters — your findings help make AI safer for millions of users
• Potential for ongoing work and contract extension as new projects launch