Remote Tigrinya Language Evaluation Specialist

AuraOne; United States; À distance; USD 34 000 - 83 000; Plein temps

Avantages offerts par ce poste

Remote work

Independent contractor

Résumé du poste

AI Trainer Jobs is seeking a Tigrinya Language Expert to remotely review prompts and model outputs against AuraOne's rubric. You will label edge cases and provide structured feedback to help retrain the data.

AI data reviewers turn evaluation outputs into auditable labels, rationales, and regression cases for human data programs. Responsibilities include evaluating outputs, comparing paired responses with rationale, and tagging content for policy adherence.

Qualifications

• Prior evaluation, annotation, or human-rater experience in Tigrinya language evaluation.
• Ability to apply rubrics consistently across long batches.
• Clear written reasoning naming issues and rubric clauses.

Responsabilités

• Evaluate model outputs against rubrics and assign severity tags.
• Compare paired responses and select the stronger answer with rationale.
• Label hallucinations, instruction-following, and unsafe content with structured tags.
• Capture ambiguous prompts and route for rubric updates.
• Maintain reviewer-quality scores by calibration against gold-standard examples.

Connaissances

Evaluation experience

Annotation experience

Tigrinya language knowledge

Strong written reasoning

Reliability for 10 hours per week

Description du poste

AI Trainer Jobs is seeking a Tigrinya Language Expert to remotely review prompts and model outputs against AuraOne's rubric. You will label edge cases and provide structured feedback to help retrain the data.

AI data reviewers turn evaluation outputs into auditable labels, rationales, and regression cases for human data programs. Responsibilities include evaluating outputs, comparing paired responses with rationale, and tagging content for policy adherence.