Remote Cantonese Psychologist (PhD) - Evaluation Lead

AuraOne, Inc.; United States; Remote; USD 34.000 - 55.000; Teilzeit

Zusammenfassung

AuraOne, Inc. seeks a Bilingual Cantonese Psychologist (PhD) to remotely review cantonese generalist prompts and responses against our quality rubric. You will assess paired outputs, label edge cases, and craft structured feedback for retraining to guide model improvements.

This independent contractor role requires meticulous reasoning, rubric alignment, and regular calibration against gold-standard examples. Remote—US-eligible, 10+ hours weekly.

Qualifikationen

• Prior evaluation, annotation, or human-rater experience on cantonese generalist evaluation or adjacent content for Bilingual Cantonese Psychologist (PhD) 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.

Aufgaben

• Evaluate cantonese generalist evaluation model outputs against a versioned rubric and assign severity tags for Bilingual Cantonese Psychologist (PhD) 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.

Kenntnisse

Model output evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

Cantonese generalist evaluation

Ausbildung

PhD in Psychology

Jobbeschreibung

AuraOne, Inc. seeks a Bilingual Cantonese Psychologist (PhD) to remotely review cantonese generalist prompts and responses against our quality rubric. You will assess paired outputs, label edge cases, and craft structured feedback for retraining to guide model improvements.

This independent contractor role requires meticulous reasoning, rubric alignment, and regular calibration against gold-standard examples. Remote—US-eligible, 10+ hours weekly.