Remote Vision-Language-Action Evaluation Specialist

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

Job summary

AuraOne is seeking a remote evaluation contractor to review vision-language-action task prompts and responses against our quality rubric. You will compare paired model outputs, label edge cases, and provide structured feedback for retraining.

Responsibilities include labeling hallucinations, instruction-following failures, and unsafe content with rubric-based tags, and maintaining calibration against gold-standard examples each week.

Qualifications

• Prior evaluation, annotation, or human-rater experience on vision language action task 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.
• Strong attention to detail and ability to flag when a prompt itself is the problem.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Evaluate vision language action task evaluation model outputs against a versioned rubric and assign severity tags for Vision-Language-Action Task 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

Evaluation experience

Annotation experience

Human rater experience

Vision-Language-Action

Inter-rater calibration

Attention to detail

Education

Linguistics background

Content moderation / trust & safety

Tools

Rubric-based annotation tools

Calibration tools

Job description

AuraOne is seeking a remote evaluation contractor to review vision-language-action task prompts and responses against our quality rubric. You will compare paired model outputs, label edge cases, and provide structured feedback for retraining.

Responsibilities include labeling hallucinations, instruction-following failures, and unsafe content with rubric-based tags, and maintaining calibration against gold-standard examples each week.