Chinese-Speaking Personalized AI Response Evaluator

You will evaluate a conversational AI personalization feature in Chinese. Your work will combine creative prompt writing with careful review of model responses and clear written feedback.

You will use personal experiences to create multi-turn conversations, check whether the model uses relevant context correctly, and document evidence for your judgments. You will also inspect debugging details and delete evaluation conversations after review.

• Design and run conversations that usually span one to five turns.
• Test whether claims about a user are supported by evidence instead of incorrect inferences or hallucinations.
• Compare two responses for helpfulness, ease of use, enjoyment, naturalness, and appropriate use of context.
• Write concise rationales that refer to specific turns and explain positive or negative findings.
• Check whether summaries and relevant data sources were used correctly in the debugging information.
• Delete evaluation conversations after review so future chat history stays clean.

What it pays and takes

This is an entry-level, remote contractor engagement lasting three months. The work is open worldwide, but you must be highly proficient in reading and writing Chinese and able to overlap with Pacific Time.

• Pay: $15 per hour.
• Schedule: 20 or more hours per week, with at least four hours per day and up to 40 hours per week.
• Time zone: Four hours of overlap with Pacific Time is required.
• Language: High proficiency in written and reading Chinese.
• Experience: Ability to create creative multi-turn prompts from personal context.
• Knowledge: Understanding of personalization quality, grounding, incorrect inferences, and forced connections.
• Skills: Strong attention to subtle response differences, clear writing, detailed annotation, and constructive feedback.
• Education: A bachelor's degree or equivalent experience in policy, law, ethics, linguistics, journalism, computer science, or a related analytical field.
• Preferred background: Data annotation, AI quality evaluation, content moderation, or a related area.

How it works

Apply on OpenTrain with your resume and then complete the application on the hiring site.

About AI training work

AI training work is the human side of building artificial intelligence. People review and improve model responses so AI systems can become more accurate, useful, and natural, while OpenTrain is the hiring and contracting organization for this role.