Mexican Spanish Evaluator (Remote) | Model QA & Feedback

AI Trainer Jobs; United States; Remote; USD 14,000 - 21,000; Part time

Job summary

AI Trainer Jobs seeks a Mexican Spanish expert for a remote evaluation track to review Spanish generalist prompts and responses against AuraOne's quality rubric. Reviewers compare paired outputs, label edge cases, and write structured feedback for retraining the modeling team.

Role focuses on evaluating outputs, tagging issues, and maintaining calibration through weekly gold-standard comparisons. Contractor arrangement with flexible hours, ~10 hours weekly, remote work eligible for US-based

Qualifications

• Experience evaluating Spanish generalist outputs.
• Ability to apply multi-page rubrics consistently.
• Clear written reasoning naming issues and rubric clauses.
• Attention to detail and ability to flag prompt problems.
• Reliable availability for at least 10 hours per week.

Responsibilities

• Evaluate spanish generalist evaluation model outputs against a versioned rubric and assign severity tags for Mexican Spanish 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.

Skills

Spanish evaluation experience

Rubric-based annotation

Inter-rater calibration

Attention to detail

Async availability 10h/wk

Job description

AI Trainer Jobs seeks a Mexican Spanish expert for a remote evaluation track to review Spanish generalist prompts and responses against AuraOne's quality rubric. Reviewers compare paired outputs, label edge cases, and write structured feedback for retraining the modeling team.

Role focuses on evaluating outputs, tagging issues, and maintaining calibration through weekly gold-standard comparisons. Contractor arrangement with flexible hours, ~10 hours weekly, remote work eligible for US-based