Remote Retrieval QA Specialist - Relevance & Feedback

AI Trainer Jobs; United States; Remote; USD 41,000 - 83,000; Part time

Job summary

AI Trainer Jobs is seeking a Remote Retrieval Relevance Research QA Specialist to evaluate model outputs against a versioned rubric, assign severity tags, and provide structured feedback to retrain AuraOne. You will compare paired responses and label edge cases with clear rationales, while ensuring consistency across long batches.

The role requires attention to detail, strong written reasoning, and reliable async availability for at least 10 hours per week, with US-eligible remote work and a

Qualifications

• Prior evaluation, annotation, or human-rater experience on retrieval relevance research QA 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.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Evaluate retrieval relevance research QA model outputs against a versioned rubric and assign severity tags.
• Compare paired responses and pick the stronger answer with a written rationale.
• Label hallucinations, instruction-following failures, and unsafe content with structured tags.

Skills

Prior evaluation experience

Attention to detail

Clear written reasoning

Remote work experience

Tools

Rubric-based annotation

Inter-rater calibration

Browser tools

Job description

AI Trainer Jobs is seeking a Remote Retrieval Relevance Research QA Specialist to evaluate model outputs against a versioned rubric, assign severity tags, and provide structured feedback to retrain AuraOne. You will compare paired responses and label edge cases with clear rationales, while ensuring consistency across long batches.

The role requires attention to detail, strong written reasoning, and reliable async availability for at least 10 hours per week, with US-eligible remote work and a