Remote Video Evaluation Specialist (US-Based)

AuraOne; United States; On-site; USD 20,664 - 34,440; Part time

Job summary

AuraOne is seeking a remote Video Capture Generalist for US-based evaluation tasks. You will review model outputs, apply rubrics, and provide structured feedback to retrain the system. This contractor role emphasizes careful labeling of errors, edge cases, and unsafe content.

Responsibilities include comparing responses, marking strongest outputs with rationale, and maintaining calibration against gold-standard examples on a weekly cadence. 10+ hours weekly availability requested.

Qualifications

• Prior evaluation, annotation, or human-rater experience on video capture generalist US-based 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.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Evaluate video capture generalist US-based evaluation model outputs against a versioned rubric and assign severity tags.
• Compare paired responses and pick the stronger answer with 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

Rubric application

Written reasoning

Attention to detail

Async availability

Job description

AuraOne is seeking a remote Video Capture Generalist for US-based evaluation tasks. You will review model outputs, apply rubrics, and provide structured feedback to retrain the system. This contractor role emphasizes careful labeling of errors, edge cases, and unsafe content.

Responsibilities include comparing responses, marking strongest outputs with rationale, and maintaining calibration against gold-standard examples on a weekly cadence. 10+ hours weekly availability requested.