Find your next role
Discover roles across ambitious teams
7,353 jobs
- More jobs
micro1
Domain Contributor, Evaluation Specialist
Remote · Mid level
$30–$60 / hour
About the role
Support an internal project evaluating and improving advanced AI models by applying your expertise. Help train next-generation AI systems with high-quality, real-world input across various domains.
What you’ll do
• Design domain-specific tasks probing AI model limits. • Author questions requiring deep subject knowledge. • Assess AI outputs against authoritative sources. • Document rationales for model shortcomings. • Apply task guidelines and evaluation rubrics consistently.
What you’ll bring
• Experience with AI model training or evaluation. • Expertise in history, law, finance, journalism, or tech. • Advanced research skills verifying complex claims. • Strong written and verbal communication. • Ability to follow detailed instructions and frameworks.