AI Red Team Tester

Alignerr Corp.; United States; Remote; GBP 28,000 - 83,000; Part time

Job summary

Alignerr is seeking AI Red Team Testers for a fully remote hourly contract. You will creatively challenge AI models to expose weaknesses, uncover unsafe outputs, and help build a safer AI ecosystem.

The role offers flexible hours and collaboration with a global team of researchers and testers. Ideal candidates are curious thinkers who can design prompts and scenarios, document failures clearly, and communicate findings with precision.

Qualifications

• Must be comfortable adopting an adversarial mindset and thinking unconventionally.
• Detail-oriented and systematic — you document findings clearly and thoroughly.
• Strong written communicator who can explain issues with precision.
• Self-motivated and able to work independently on flexible, task-based assignments.

Responsibilities

• Design imaginative prompts, scenarios, and strategies to expose AI weaknesses.
• Attempt to elicit incorrect, unsafe, biased, or inappropriate outputs from AI models.
• Document every failure mode with clear, reproducible steps.
• Rate the severity and potential impact of discovered issues.
• Provide structured, actionable feedback to safety and research teams.
• Collaborate asynchronously with a global team of researchers and testers.

Skills

Adversarial thinking

Attention to detail

Written communication

Independent work

Curious mindset

Job description

About The Role

What if your job was to think like an adversary — to probe, pressure-test, and outwit some of the most advanced AI systems in the world? We're looking for AI Red Team Testers to do exactly that. You'll creatively challenge AI models to expose weaknesses, uncover unsafe outputs, and help build a safer AI ecosystem.

About The Role

What if your job was to think like an adversary — to probe, pressure-test, and outwit some of the most advanced AI systems in the world? We're looking for AI Red Team Testers to do exactly that. You'll creatively challenge AI models to expose weaknesses, uncover unsafe outputs, and help build a safer AI ecosystem.

This is a fully remote, flexible contract role open to curious, critical thinkers of all backgrounds. If you enjoy puzzles, spotting flaws others miss, and thinking outside the box, this role was built for you.

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

What You'll Do

• Design imaginative prompts, scenarios, and strategies to expose AI weaknesses
• Attempt to elicit incorrect, unsafe, biased, or inappropriate outputs from AI models
• Document every failure mode you find with clear, reproducible steps
• Rate the severity and potential impact of discovered issues
• Provide structured, actionable feedback to safety and research teams
• Collaborate asynchronously with a global team of researchers and testers

Who You Are

• A naturally curious and creative thinker who enjoys probing for weaknesses
• Comfortable adopting an adversarial mindset and thinking unconventionally
• Detail-oriented and systematic — you document what you find clearly and thoroughly
• Strong written communicator who can explain issues with precision
• Self-motivated and able to work independently on flexible, task-based assignments
• No hacking, security, or AI background required — just sharp thinking and genuine curiosity

Nice to Have

• Experience in writing, research, journalism, psychology, or critical analysis
• Familiarity with AI chatbots or language models as an end user
• Background in QA, ethics, policy, or academic research
• An interest in AI safety and responsible AI development

Why Join Us

• Work on cutting-edge AI projects alongside leading research labs
• Fully remote and flexible — set your own schedule and work at your own pace
• Freelance autonomy with meaningful, intellectually stimulating work
• Make a tangible contribution to AI safety and the responsible development of AI
• Potential for ongoing work and contract extension as new projects launch