Remote Colombian Spanish AI Quality Evaluator

AuraOne Human Data; United States; Remote; USD 11,000 - 16,000; Full time

Job summary

AuraOne, Inc. seeks a Remote Colombian Spanish Expert — AI Language Evaluation contractor to review Spanish generalist outputs against a versioned rubric. You will compare outputs, label issues, and provide structured feedback to retrain models.

The role requires 10 hours per week commitment and strong written reasoning. Responsibilities include identifying errors, tagging content, and calibrating your judgments with gold-standard samples to maintain accuracy.

Qualifications

• Experience evaluating Spanish generalist content or adjacent material.
• Ability to apply multi-page rubrics consistently across batches.
• Clear written reasoning that names the issue and rubric clause applied.
• Strong attention to detail and ability to flag when a prompt is the problem.

Responsibilities

• Evaluate Spanish generalist evaluation model outputs against a versioned rubric and assign severity tags.
• Compare paired responses and select 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 to guide future training iterations.

Skills

Model output evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

Spanish generalist evaluation

Job description

AuraOne, Inc. seeks a Remote Colombian Spanish Expert — AI Language Evaluation contractor to review Spanish generalist outputs against a versioned rubric. You will compare outputs, label issues, and provide structured feedback to retrain models.

The role requires 10 hours per week commitment and strong written reasoning. Responsibilities include identifying errors, tagging content, and calibrating your judgments with gold-standard samples to maintain accuracy.