Human Feedback Specialist

We are hiring Human Feedback Specialists to provide critical preference and safety data. You will review model completions, simulate target users, and label response features.

What you'll do

• Provide preference ratings on generated text across a range of domain topics
• Assess responses for toxicity, helpfulness, and style alignment
• Simulate realistic conversations to test boundary conditions of LLM systems
• Document failures, bias, or safety exceptions with detailed evidence

What we're looking for

• Excellent analytical skills and ability to evaluate text objectivity
• High level of compliance with instructions and guidelines
• Familiarity with internet safety concepts and content moderation standards
• Strong verbal and written English communication skills

Benefits & Perks

• Highly flexible remote hours
• Continuous stream of learning and evaluation projects
• Collaborative and supportive community of contributors
• Help build a safer, more aligned future for artificial intelligence