What if your curiosity and critical thinking could directly shape the safety of AI systems used by millions of people? We are looking for AI Safety Analysts to put cutting-edge AI models to the test — probing for harmful outputs, uncovering blind spots, and helping ensure these systems behave responsibly in the real world.

This is a fully remote, flexible contract role open to anyone with a sharp, questioning mind and strong written communication skills. No cybersecurity or AI background required.

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

• Test AI systems by crafting challenging, adversarial, and edge-case inputs designed to expose weaknesses
• Identify unsafe, harmful, biased, or otherwise problematic AI outputs
• Document safety issues clearly with detailed examples and structured explanations
• Rate AI responses...