About This Role
Evaluating prompts and responses for swift evaluation against a quality rubric is the core of this remote evaluation role. You will compare paired outputs, label edge cases, and write structured feedback for the modeling team to use in retraining.
Responsibilities
- Evaluate swift evaluation model outputs against a versioned rubric and assign severity tags for Swift Evaluator 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
- Document recurring failure modes so the modeling team can target them in the next training run
Requirements
- Prior evaluation, annotation, or human-rater experience on swift evaluation or adjacent content for Swift Evaluator 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
Nice to have:
- 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
Important Details
- Work model: Independent specialist contractor
- Employment type: CONTRACTOR
Application Process
- Apply through AuraOne's specialist intake for role-specific routing and review
- Final project scope, schedule, and contractor terms are confirmed before placement
About the Company
AI data reviewers help turn swift evaluation outputs into auditable labels, rationales, and regression cases for AuraOne Human Data.