AI Red Team Tester

About the role

Join Alignerr as an AI Red Team Tester and use your curiosity and creativity to help make advanced AI systems safer. In this fully remote, flexible contract position you will think like an adversary, probing AI models for weaknesses before they can cause real‑world harm.

Key responsibilities

• Design creative, adversarial prompts and scenarios aimed at exposing AI weaknesses.
• Attempt to elicit incorrect, unsafe, biased, or inappropriate outputs from AI models.
• Document every failure mode with clear, reproducible steps.
• Rate and categorize the severity of issues according to 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.

Required profile

• Creative, curious thinker who enjoys puzzles, thought experiments, and finding system flaws.
• Comfortable thinking adversarially and asking “what could go wrong?”.
• Detail‑oriented and systematic in documenting findings.
• Strong written communication skills in English.
• Self‑motivated and able to work independently on task‑based assignments.

Required skills

What we offer

• Fully remote, flexible schedule – work from anywhere.
• Hourly contract with potential for ongoing work and extensions.
• Opportunity to contribute to meaningful AI safety projects alongside leading research labs.