Remote Mandarin Evaluator & Rubric Annotator (Traditional)

AuraOne; United States; On-site; USD 25,000 - 28,000; Part time

Job summary

AuraOne seeks a Bilingual Writer for Mandarin Chinese (Traditional, Taiwan) to remotely evaluate model outputs against a quality rubric. You will compare responses, label edge cases, and provide structured feedback to retrain models.

This is a CONTRACTOR role with US-remote eligibility and requires reliable async availability to support ongoing evaluation tasks. Applicants should demonstrate strong attention to detail, clear written rationales tied to rubric clauses, and experience with mandarin

Qualifications

• Experience evaluating mandarin generalist content using rubrics.
• Ability to write clear rationales tied to rubric clauses.
• Strong attention to detail and ability to flag prompt issues.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Evaluate mandarin generalist evaluation outputs against a rubric and assign severity tags.
• Compare paired responses and select the stronger one with rationale.
• Label hallucinations, instruction-following failures, and unsafe content with tags.
• Capture ambiguous prompts and route them for rubric updates.
• Maintain reviewer-quality scores by calibrating against gold-standard examples.
• Document recurring failure modes for model training improvements.

Skills

Model output evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

Mandarin generalist evaluation

Job description

AuraOne seeks a Bilingual Writer for Mandarin Chinese (Traditional, Taiwan) to remotely evaluate model outputs against a quality rubric. You will compare responses, label edge cases, and provide structured feedback to retrain models.

This is a CONTRACTOR role with US-remote eligibility and requires reliable async availability to support ongoing evaluation tasks. Applicants should demonstrate strong attention to detail, clear written rationales tied to rubric clauses, and experience with mandarin