German Evaluation Specialist (Remote Contractor)

AuraOne; United States; On-site; USD 28,000 - 55,000; Full time

Benefits offered by this job

Remote work

Job summary

AuraOne is seeking a German Transcription Expert to remotely review prompts and responses against AuraOne's quality rubric. You will compare paired outputs, label edge cases, and write structured feedback for retraining the model.

This role helps convert german generalist outputs into auditable labels, rationales, and regression cases for AuraOne Human Data, ensuring accuracy and consistency across batches.

Qualifications

• Prior evaluation, annotation, or human-rater experience on german generalist evaluation or adjacent content for German Transcription Expert work.
• Clear written reasoning that names the issue and the rubric clause being applied.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Evaluate german generalist evaluation model outputs against a versioned rubric and assign severity tags for German Transcription Expert 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

German generalist evaluation

Job description

AuraOne is seeking a German Transcription Expert to remotely review prompts and responses against AuraOne's quality rubric. You will compare paired outputs, label edge cases, and write structured feedback for retraining the model.

This role helps convert german generalist outputs into auditable labels, rationales, and regression cases for AuraOne Human Data, ensuring accuracy and consistency across batches.