AI Safety Red Team Tester (Remote, Flexible Hours)

Alignerr Corp.; Italy; Remote; EUR 34,000 - 69,000; Part time

Job summary

Alignerr is seeking AI Red Team Testers to probe AI systems, uncover weaknesses, and help improve safety. This role emphasizes creative thinking, puzzle-solving, and the ability to articulate findings clearly in an async, remote setting.

The position is an hourly contract with flexible hours (10–40 hours/week), allowing you to contribute to meaningful work from anywhere. No cybersecurity background is required, making this a project-focused opportunity for curious, disciplined individuals.

Responsibilities

• Design prompts, scenarios, and strategies to expose AI weaknesses
• Attempt to elicit unsafe, biased, or problematic outputs from AI models
• Document failure modes with clear steps to reproduce each issue
• Assess severity and impact of each vulnerability found
• Collaborate asynchronously with safety and research teams to prioritize fixes
• Help make AI systems more robust, fair, and trustworthy

Skills

Problem solving

Adversarial thinking

Attention to detail

Written communication

Self-motivation

Independent work

Job description

Alignerr is seeking AI Red Team Testers to probe AI systems, uncover weaknesses, and help improve safety. This role emphasizes creative thinking, puzzle-solving, and the ability to articulate findings clearly in an async, remote setting.

The position is an hourly contract with flexible hours (10–40 hours/week), allowing you to contribute to meaningful work from anywhere. No cybersecurity background is required, making this a project-focused opportunity for curious, disciplined individuals.