Remote Multimodal Evaluation Specialist

AI Trainer Jobs; United States; Remote; USD 34,000 - 55,000; Part time

Job summary

AI Trainer Jobs is seeking a remote Multimodal Instruction-Following Evaluator to support AuraOne's quality rubric. You will review model outputs across text, images, and documents, assign severity tags, and provide structured feedback for retraining.

The contractor role offers an hourly rate confirmed after interview, with independent work and reliable async availability for at least 10 hours weekly. Remote work is supported from the United States.

Qualifications

• Experience evaluating multimodal instruction-following evaluation or related content.
• Ability to apply rubrics consistently across large batches.
• Clear written rationale naming the issue and rubric clause.
• Strong attention to detail and accuracy in labels.
• Reliable asynchronous availability for at least 10 hours per week.

Responsibilities

• Evaluate model outputs against a versioned rubric and assign severity tags.
• Compare paired responses and select the stronger answer with rationale.
• Label hallucinations, instruction-following failures, and unsafe content with structured tags.
• Capture ambiguous prompts and route to program team for rubric updates.

Skills

Evaluation experience

Rubrics

Written reasoning

Attention to detail

Async availability

Job description

AI Trainer Jobs is seeking a remote Multimodal Instruction-Following Evaluator to support AuraOne's quality rubric. You will review model outputs across text, images, and documents, assign severity tags, and provide structured feedback for retraining.

The contractor role offers an hourly rate confirmed after interview, with independent work and reliable async availability for at least 10 hours weekly. Remote work is supported from the United States.