Role OverviewReview recorded sessions where users interact with an AI assistant via voice and camera, comparing the assistant's responses to visible video content, and scoring sessions on visual interpretation, accuracy, relevance, and response timing.
What You Will Do
Evaluate the assistant's use of spatial and directional language, judge the appropriateness and timing of warnings related to health, safety, or financial security, and write detailed comments supporting scores with concrete session evidence.
Why It Might Be a Fit
Must have native or native-level Korean, spoken and written, and clear, precise written Korean. Preferred experience in data annotation, linguistic QA, content moderation, or AI model evaluation, or training in linguistics, translation, or interpreting.
Requirements
- Native or native-level Korean, spoken and written
- Clear, precise written Korean
- An Android phone with a working camera and microphone
- Attention to detail and consistent rubric application
- Professional English reading comprehension
Benefits
- Compensation: $24–$30/hour
]]>