Remote Object Detection Evaluation Specialist

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

Job summary

AuraOne is seeking a remote contractor to evaluate object detection failure analyst outputs against a versioned rubric. You will compare paired responses, label edge cases, and provide structured feedback to retrain models.

This role emphasizes clear written reasoning, consistent rubric application, and calibration against gold-standard examples weekly. Applicants must be eligible to work from the United States and be comfortable asynchronously.

Qualifications

• Prior evaluation, annotation, or human-rater experience on object detection 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 object detection failure analyst evaluation model outputs against a versioned rubric and assign severity tags for Object Detection Failure Analyst 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 evaluation

Rubric annotation

Severity tagging

Inter-rater calibration

Computer vision

Spatial reasoning

Video QA

Edge case labeling

Job description

AuraOne is seeking a remote contractor to evaluate object detection failure analyst outputs against a versioned rubric. You will compare paired responses, label edge cases, and provide structured feedback to retrain models.

This role emphasizes clear written reasoning, consistent rubric application, and calibration against gold-standard examples weekly. Applicants must be eligible to work from the United States and be comfortable asynchronously.