AI Red Team Tester

Alignerr Corp.; Italia; Remote; EUR 25,000 - 74,000; Part time

Job summary

Alignerr is seeking AI Red Team Testers to probe, challenge, and stress-test AI systems, identifying weaknesses before they cause real-world harm. This remote hourly contract offers 10–40 hours per week and the flexibility to work from anywhere.

You will design prompts and scenarios, attempt to elicit problematic outputs, document failure modes, and rate severity. You’ll collaborate asynchronously with safety researchers to help prioritize fixes and improve AI safety at scale.

Qualifications

• You thrive on solving problems and spotting the unexpected.
• Comfortable thinking adversarially, asking what could go wrong.
• Detail‑oriented with clear documentation.
• Strong written communication, concise and precise.
• Self-motivated and able to work asynchronously.
• No cybersecurity or hacking background required.

Responsibilities

• Design prompts, scenarios, and conversational strategies to expose AI weaknesses.
• Attempt to elicit incorrect, unsafe, biased, or problematic outputs from AI models.
• Document discovered failure modes with clear reproduction steps.
• Assess and rate the severity and potential impact of each vulnerability.
• Collaborate asynchronously with AI safety and research teams to prioritize fixes.
• Contribute to making AI systems more robust, fair, and trustworthy.

Skills

Problem solving

Adversarial thinking

Detail oriented

Written communication

Independent worker

No cybersecurity background

Job description

About The Role

What if your curiosity, creativity, and knack for thinking outside the box could make AI safer for everyone? We're looking for AI Red Team Testers to do exactly that — probing, challenging, and stress-testing AI systems to uncover weaknesses before they cause real-world harm.

About The Role

What if your curiosity, creativity, and knack for thinking outside the box could make AI safer for everyone? We're looking for AI Red Team Testers to do exactly that — probing, challenging, and stress-testing AI systems to uncover weaknesses before they cause real-world harm.

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

What You'll Do

• Design creative prompts, scenarios, and conversational strategies to expose AI weaknesses
• Attempt to elicit incorrect, unsafe, biased, or otherwise problematic outputs from AI models
• Document discovered failure modes in detail, including clear steps to reproduce each issue
• Assess and rate the severity and potential impact of each vulnerability you find
• Collaborate asynchronously with AI safety and research teams to help prioritize fixes
• Contribute directly to making AI systems more robust, fair, and trustworthy

Who You Are

• A natural problem-solver who enjoys finding the unexpected angle
• Comfortable thinking adversarially — you like to ask "what could go wrong?"
• Detail-oriented and systematic, with the discipline to document findings clearly
• Strong written communicator who can explain issues concisely and precisely
• Self-motivated and able to work independently in an async environment
• No cybersecurity, hacking, or technical background required

Nice to Have

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

Why Join Us

• Work on genuinely important problems alongside leading AI research labs
• Fully remote and flexible — set your own hours and work from anywhere
• Freelance autonomy with meaningful, intellectually stimulating work
• Play a direct role in shaping how AI behaves and improving safety at scale
• Potential for ongoing work and contract extension as new projects launch