Remote Visual QA Evaluator & Rubric Auditor

AuraOne; United States; On-site; USD 34,440 - 55,104; Part time

Job summary

AuraOne seeks a Visual Question Answering Model Evaluator to review evaluation prompts and model outputs against AuraOne's quality rubric. This remote contractor role supports the AuraOne Human Data team by labeling edge cases, scoring outputs, and providing structured feedback for retraining.

Responsibilities include comparing responses, tagging issues, calibrating scores weekly against gold standards, and documenting recurring failure modes for rubric updates.

Qualifications

• Prior evaluation, annotation, or human-rater experience on visual question answering model evaluation or adjacent content.

Responsibilities

• Evaluate visual question answering model evaluation 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.
• 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.

Skills

Model output evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

Multimodal evaluation

Cross-modal reasoning

Grounding review

Job description

AuraOne seeks a Visual Question Answering Model Evaluator to review evaluation prompts and model outputs against AuraOne's quality rubric. This remote contractor role supports the AuraOne Human Data team by labeling edge cases, scoring outputs, and providing structured feedback for retraining.

Responsibilities include comparing responses, tagging issues, calibrating scores weekly against gold standards, and documenting recurring failure modes for rubric updates.