Remote Portuguese AI Evaluation & Annotation Specialist

AuraOne, Inc.; United States; Remote; USD 57,000 - 81,000; Full time

Job summary

AuraOne, Inc. is seeking Portuguese Linguistic Experts for AI Evaluation & Annotation (Remote).

This remote evaluation track reviews Portuguese prompts and responses against AuraOne's quality rubric, compares paired outputs, and writes structured feedback to retrain the model. Responsibilities include labeling edge cases, marking hallucinations or policy violations with severity tags, calibrating scores weekly, and documenting recurring failures for the program team.

Qualifications

• Prior evaluation, annotation, or human-rater experience on Portuguese 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 portuguese generalist evaluation model outputs against a versioned rubric and assign severity tags for Portuguese Linguistic Experts — AI Evaluation & Annotation (Remote) 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

Portuguese generalist evaluation

Job description

AuraOne, Inc. is seeking Portuguese Linguistic Experts for AI Evaluation & Annotation (Remote).

This remote evaluation track reviews Portuguese prompts and responses against AuraOne's quality rubric, compares paired outputs, and writes structured feedback to retrain the model. Responsibilities include labeling edge cases, marking hallucinations or policy violations with severity tags, calibrating scores weekly, and documenting recurring failures for the program team.