Remote Image Segmentation QA Analyst

AuraOne; United States; On-site; USD 34,440 - 61,992; Part time

Job summary

AuraOne is seeking a remote Evaluation Analyst to review image segmentation failure analyses. You will apply a versioned rubric to model outputs, assign severity tags, and select the stronger responses with rationale.

You will also label hallucinations, instruction-following failures, and unsafe content with structured tags. The role requires clear written reasoning, strong attention to detail, and reliable async availability for at least 10 hours per week.

Qualifications

• Prior evaluation, annotation, or human-rater experience on image segmentation failure analyst evaluation or adjacent content.
• Ability to apply 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 image segmentation failure analyst evaluation 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.
• 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 evaluation

Rubric annotation

Severity tagging

Inter-rater calibration

Computer vision

Spatial reasoning

Video QA

Job description

AuraOne is seeking a remote Evaluation Analyst to review image segmentation failure analyses. You will apply a versioned rubric to model outputs, assign severity tags, and select the stronger responses with rationale.

You will also label hallucinations, instruction-following failures, and unsafe content with structured tags. The role requires clear written reasoning, strong attention to detail, and reliable async availability for at least 10 hours per week.