Chinese Voice Coach (Mandarin)

AuraOne Human Data; United States; Remote; USD 41,000 - 83,000; Full time

Job summary

AuraOne, Inc. is seeking an AI data reviewer to evaluate Chinese generalist evaluation model outputs (Mandarin) against a versioned rubric. You will compare responses, select the stronger answer with rationale, and tag hallucinations or unsafe content using structured rubric categories.

The role requires clear written reasoning, attention to detail, and at least 10 hours per week of async availability. Remote access from the US is supported as a contractor position.

Qualifications

• Prior evaluation, annotation, or human-rater experience on chinese generalist evaluation or adjacent content for Chinese Voice Coach (Mandarin) work.
• Comfort applying multi-page rubrics consistently across long batches.
• Clear written reasoning that names the issue and the rubric clause being applied.
• Strong attention to detail and the ability to flag when a prompt itself is the problem.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Evaluate chinese generalist evaluation model outputs against a versioned rubric and assign severity tags for Chinese Voice Coach (Mandarin) assignments.
• Compare paired responses and pick the stronger answer with a written rationale.
• Label hallucinations, instruction-following failures, and unsafe content with structured tags.
• Capture ambiguous prompts and route them back to the program team for rubric updates.
• Maintain reviewer-quality scores by calibrating against gold-standard examples each week.
• Document recurring failure modes so the modeling team can target them in the next training run.

Skills

Model output evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

Chinese generalist evaluation

Job description

Why this role matters

AI data reviewers help turn chinese generalist evaluation outputs into auditable labels, rationales, and regression cases for AuraOne Human Data.

Responsibilities

• Evaluate chinese generalist evaluation model outputs against a versioned rubric and assign severity tags for Chinese Voice Coach (Mandarin) assignments.
• Compare paired responses and pick the stronger answer with a written rationale.
• Label hallucinations, instruction-following failures, and unsafe content with structured tags.
• Capture ambiguous prompts and route them back to the program team for rubric updates.
• Maintain reviewer-quality scores by calibrating against gold-standard examples each week.
• Document recurring failure modes so the modeling team can target them in the next training run.

Qualifications

• Prior evaluation, annotation, or human-rater experience on chinese generalist evaluation or adjacent content for Chinese Voice Coach (Mandarin) work.
• Comfort applying multi-page rubrics consistently across long batches.
• Clear written reasoning that names the issue and the rubric clause being applied.
• Strong attention to detail and the ability to flag when a prompt itself is the problem.
• Reliable async availability for at least 10 hours per week.

Example tasks

• Compare two chinese generalist evaluation model responses to the same prompt and pick the stronger one with rationale.
• Tag an unsafe response with the correct policy category and severity.
• Audit a 50-row batch for rubric consistency and report drift to the program lead.
• Propose a rubric clarification after spotting a recurring failure mode.

Nice to have

• Background in linguistics, content moderation, or trust & safety review.
• Experience with inter-rater agreement metrics and calibration cycles.
• Domain expertise that lets you spot subject-matter errors automated checks miss.

Skills

• Model output evaluation
• Rubric-based annotation
• Severity tagging
• Inter-rater calibration
• Chinese generalist evaluation

Work model

Remote — US-eligible. Remote · Independent specialist contractor. Employment type: CONTRACTOR. Applicants must be authorized to work from US.

Compensation

$30-$60/hour

Prior evaluation, annotation, or human-rater experience on chinese generalist evaluation or adjacent content for Chinese Voice Coach (Mandarin) work. Comfort applying multi-page rubrics consistently across long batches. Clear written reasoning that names the issue and the rubric clause being applied. Strong attention to detail and the ability to flag when a prompt itself is the problem. Reliable async availability for at least 10 hours per week.