French AI Evaluation & Transcription Specialist (Remote)

AuraOne, Inc.; United States; Remote; USD 30,000 - 48,000; Full time

Job summary

AuraOne, Inc. is seeking a French Transcription Expert (France) for a remote evaluation track. The role involves reviewing french generalist evaluation prompts and responses against the company quality rubric and providing structured feedback for retraining.

You will compare paired outputs, label edge cases, and write concise rationales to help the modeling team improve data quality and detector performance.

Qualifications

• Review french generalist evaluation prompts and responses against AuraOne's quality rubric.
• Label hallucinations, instruction-following failures, and unsafe content with structured tags.
• Capture ambiguous prompts and route them to the program team for rubric updates.
• Maintain reviewer-quality scores by calibrating against gold-standard examples.
• Review paired outputs and decide the stronger answer with a written rationale.

Responsibilities

• Evaluate french generalist evaluation model outputs against a versioned rubric and assign severity tags for French Transcription Expert (France) 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.

Skills

French language proficiency

Attention to detail

Analytical thinking

Technical writing

Job description

AuraOne, Inc. is seeking a French Transcription Expert (France) for a remote evaluation track. The role involves reviewing french generalist evaluation prompts and responses against the company quality rubric and providing structured feedback for retraining.

You will compare paired outputs, label edge cases, and write concise rationales to help the modeling team improve data quality and detector performance.