Evaluators for AI training (English language)
Remote
Core
Evaluate AI agent replies to ensure safety and prevent harmful, offensive, or toxic content.
Role type
AI safety evaluator (content moderation)
Builds
Safer AI agent responses for end users
Domain
Artificial Intelligence / Content Safety
Deliverable
production ML models
Required skills
English (B2+ reading/writing), attention to detail, time management, proactive approach, curiosity
Responsibilities
Evaluate AI agent replies against guidelines, compare two responses to determine quality differences, assign absolute overall ratings to responses