AI Red Team Tester

Alignerr Corp.; Argentina; Remote; ARS 827,000 - 1,653,000; Part time

Benefits offered by this job

Remote work

Job summary

Alignerr is seeking AI Red Team Testers to think like adversaries, probing and stress-testing cutting-edge AI systems to reveal weaknesses before they cause real-world harm. This is a fully remote, hourly contract role open to anyone who enjoys puzzles, critical thinking, and documenting findings clearly.

You will design testing scenarios, elicit unsafe outputs, and collaborate with safety and research teams to improve AI reliability on a flexible schedule.

Qualifications

• Creative, curious thinker who enjoys puzzles and finding flaws in systems.
• Comfortable thinking adversarially—asks what could go wrong?
• Detail-oriented and systematic; documents findings clearly.
• Strong written communication skills in English.

Responsibilities

• Design adversarial prompts and scenarios to expose AI weaknesses.
• Attempt to elicit unsafe, biased, or incorrect outputs from AI models.
• Document failures with clear, reproducible steps.
• Rate and categorize issue severities using structured guidelines.
• Collaborate asynchronously with AI safety and research teams.

Skills

Creative thinking

Adversarial thinking

Written communication

Independent work

Job description

What if your curiosity, creativity, and knack for finding loopholes could directly make AI safer for millions of people? We're looking for AI Red Team Testers to think like an adversary—probing, challenging, and stress-testing cutting-edge AI systems to expose weaknesses before they cause real-world harm.

What if your curiosity, creativity, and knack for finding loopholes could directly make AI safer for millions of people? We're looking for AI Red Team Testers to think like an adversary—probing, challenging, and stress-testing cutting-edge AI systems to expose weaknesses before they cause real-world harm. This is a fully remote, flexible contract role open to anyone who thinks critically, loves puzzles, and enjoys finding the cracks in seemingly solid systems. No cybersecurity or hacking background required.

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

What You'll Do

• Design creative, adversarial prompts and scenarios designed to expose AI weaknesses
• Attempt to elicit incorrect, unsafe, biased, or inappropriate outputs from AI models
• Document every failure mode you discover with clear, reproducible steps
• Rate and categorize the severity of issues based on structured guidelines
• Collaborate asynchronously with AI safety and research teams to report findings
• Explore edge cases across a wide range of topics, tones, and scenarios

Who You Are

• A creative, curious thinker who enjoys puzzles, thought experiments, and finding flaws in systems
• Comfortable thinking adversarially — you naturally ask "what could go wrong?"
• Detail-oriented and systematic: you document findings clearly and thoroughly
• Strong written communication skills in English
• Self-motivated and able to work independently on task-based assignments
• No background in cybersecurity, hacking, or AI required

Nice to Have

• Experience in writing, journalism, creative fiction, or debate
• Familiarity with AI language models as an end user
• Background in ethics, philosophy, psychology, or critical analysis
• Prior experience in QA, software testing, or content evaluation

Why Join Us

• Work on meaningful AI safety projects alongside leading research labs
• Fully remote and flexible — work on your own schedule, wherever you are
• Freelance autonomy with the satisfaction of genuinely impactful work
• Contribute to making AI safer, fairer, and more reliable for everyone
• Potential for ongoing work and contract extension as new projects launch