Remote Computer Vision & Spatial Reasoning Evaluator

AuraOne; United States; On-site; USD 41,000 - 69,000; Part time

Job summary

AuraOne is seeking a remote evaluator to review computer vision and spatial reasoning prompts and responses for quality and consistency. You will compare outputs, assign severity tags, and provide structured feedback to help retrain models.

The role emphasizes clear written reasoning, attention to detail, and the ability to flag issues in prompts. Flexible remote availability and contractor status apply.

Qualifications

• Prior evaluation, annotation, or human-rater experience on computer vision and spatial reasoning evaluation or adjacent content for Computer Vision and Spatial Reasoning 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.

Responsibilities

• Evaluate computer vision and spatial reasoning evaluation model outputs against a versioned rubric and assign severity tags for Computer Vision and Spatial Reasoning 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.

Skills

Model output evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

Computer Vision and Spatial Reasoning

Robotics and physical AI

AI evaluation

Rubric writing

Expert review

Tools

Job description

AuraOne is seeking a remote evaluator to review computer vision and spatial reasoning prompts and responses for quality and consistency. You will compare outputs, assign severity tags, and provide structured feedback to help retrain models.

The role emphasizes clear written reasoning, attention to detail, and the ability to flag issues in prompts. Flexible remote availability and contractor status apply.