Retrieval Relevance Research QA Specialist

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

Retrieval Relevance Research QA Specialist is a remote evaluation track for reviewing retrieval relevance research qa evaluation prompts and responses against AuraOne's quality rubric. Reviewers compare paired outputs, label edge cases, and write the kind of structured feedback the modeling team can use to retrain.

Category: Search, Web & Browser Agents · Pay: $30–$60 / hr · Location: Remote — US-eligible · Contractor

About the role

Retrieval Relevance Research QA Specialist is a remote evaluation track for reviewing retrieval relevance research qa evaluation prompts and responses against AuraOne's quality rubric. Reviewers compare paired outputs, label edge cases, and write the kind of structured feedback the modeling team can use to retrain.
AI data reviewers help turn retrieval relevance research qa evaluation outputs into auditable labels, rationales, and regression cases for AuraOne Human Data.
Review browser automation and multi-step search agents. Check whether sources hold up.

Responsibilities

• Evaluate retrieval relevance research qa evaluation model outputs against a versioned rubric and assign severity tags for Retrieval Relevance Research QA Specialist 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.

Role details

Track Evaluation & annotation Work model Remote · Independent specialist contractor Compensation Hourly rate confirmed after the interview process. Eligible from US

What you should bring

• Prior evaluation, annotation, or human-rater experience on retrieval relevance research qa evaluation or adjacent content for Retrieval Relevance Research QA Specialist work.
• 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.

Example tasks

• Compare two retrieval relevance research qa evaluation model responses to the same prompt and pick the stronger one with rationale.
• Tag an unsafe response with the correct policy category and severity.
• Audit a 50-row batch for rubric consistency and report drift to the program lead.
• Propose a rubric clarification after spotting a recurring failure mode.

Useful experience

• Background in linguistics, content moderation, or trust & safety review.
• Experience with inter-rater agreement metrics and calibration cycles.
• Domain expertise that lets you spot subject-matter errors automated checks miss.

Compensation and schedule

Hourly rate confirmed after the interview process.
Expected arrangement: contractor , with program-defined task volume and review pacing. Placement depends on current program demand and reviewer confirmation.

Skills used in matching

• Model output evaluation
• Rubric-based annotation
• Severity tagging
• Inter-rater calibration
• Retrieval Relevance Research QA evaluation
• Web research
• Source grounding
• Browser automation
• Retrieval
• Relevance