Mandarin AI Evaluation Specialist (Remote, US-Eligible)

AuraOne; United States; À distance; USD 68 000 - 97 000; Temps partiel

Avantages offerts par ce poste

Remote — US-eligible

Résumé du poste

AuraOne is seeking Mandarin Generalist Evaluation Experts for remote, contract work. You will review model outputs against rubrics, assign severity tags, and provide rationales to support model retraining. The role requires strong attention to detail and the ability to apply rubrics across multiple pages with clear written reasoning.

Remote work is available for US-eligible contractors. Part-time weekly commitment is acceptable, with ongoing calibration against gold standards and structured

Qualifications

• Prior evaluation, annotation, or human-rater 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.

Responsabilités

• Evaluate mandarin generalist evaluation model outputs against a versioned rubric and assign severity tags for Mandarin Chinese AI Evaluation Expert (Remote, 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.

Connaissances

Model output evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

Mandarin generalist evaluation

Description du poste

AuraOne is seeking Mandarin Generalist Evaluation Experts for remote, contract work. You will review model outputs against rubrics, assign severity tags, and provide rationales to support model retraining. The role requires strong attention to detail and the ability to apply rubrics across multiple pages with clear written reasoning.

Remote work is available for US-eligible contractors. Part-time weekly commitment is acceptable, with ongoing calibration against gold standards and structured