Mandarin AI Evaluation Specialist - Remote Contractor

AuraOne, Inc.; United States; Remote; USD 72,000 - 96,000; Full time

Job summary

AuraOne, Inc. seeks a Consulting Expert for Mandarin Chinese evaluation on a remote, contractor basis. You will review model outputs against a versioned rubric, label issues, and provide structured feedback to help retrain the model.

Responsibilities include comparing responses, tagging errors, and calibrating against gold standards weekly. Strong attention to detail and experience with mandarin evaluation are required; flexibility for asynchronous collaboration is essential.

Qualifications

• Prior evaluation or annotation experience on mandarin generalist evaluation or adjacent content.
• 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 mandarin generalist evaluation model outputs against a versioned rubric and assign severity tags for Consulting Expert, Mandarin Chinese (mainland China) 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

Mandarin generalist evaluation

Job description

AuraOne, Inc. seeks a Consulting Expert for Mandarin Chinese evaluation on a remote, contractor basis. You will review model outputs against a versioned rubric, label issues, and provide structured feedback to help retrain the model.

Responsibilities include comparing responses, tagging errors, and calibrating against gold standards weekly. Strong attention to detail and experience with mandarin evaluation are required; flexibility for asynchronous collaboration is essential.