Remote AI Safety Analyst - Adversarial Testing

Alignerr is seeking an AI Safety Analyst to evaluate AI systems for safety and responsibility. This role is fully remote, ideal for critical thinkers with strong written communication skills, looking to influence AI system safety.

The successful candidate will test AI systems by designing adversarial inputs, document safety issues clearly, and work independently on a flexible schedule. A background in AI or cybersecurity is not required, making this an inviting opportunity for those passionate about responsible technology.