AI Safety Red Team Tester — Remote Contract

Alignerr Corp.; France; Remote; EUR 34,000 - 83,000; Full time

Job summary

Alignerr Corp. is seeking an AI Red Team Tester to systematically probe and challenge cutting-edge AI systems, uncover blind spots, and contribute to safety work.

This remote hourly contract role welcomes a curious, adversarial thinker who can document findings clearly and work independently in an async environment. No cybersecurity or hacking background is required, making this an inclusive opportunity for creative problem solvers across disciplines.

Qualifications

• Curious thinker who enjoys puzzles, loopholes, and unconventional ideas.
• Comfortable approaching problems from an adversarial angle — you like finding what others miss.
• Detail-oriented and systematic: you document findings clearly and thoroughly.
• Strong written communicator who can articulate issues with precision.
• Self-motivated and reliable when working independently in an async environment.
• No background in cybersecurity, hacking, or AI required.

Responsibilities

• Design inventive prompts, scenarios, and conversational strategies to expose weaknesses in AI systems.
• Attempt to elicit incorrect, unsafe, biased, or inappropriate outputs from AI models.
• Document failure modes in clear, reproducible detail so they can be addressed by research teams.
• Assess and rate the severity of issues you discover using structured evaluation frameworks.
• Collaborate asynchronously with AI safety and research teams to inform model improvements.
• Explore edge cases across a wide range of topics, tones, and contexts.

Skills

Curious thinker

Adversarial mindset

Detail oriented

Strong writing

Self-motivated

Job description

Alignerr Corp. is seeking an AI Red Team Tester to systematically probe and challenge cutting-edge AI systems, uncover blind spots, and contribute to safety work.

This remote hourly contract role welcomes a curious, adversarial thinker who can document findings clearly and work independently in an async environment. No cybersecurity or hacking background is required, making this an inclusive opportunity for creative problem solvers across disciplines.