Remote Video Instruction Evaluation Specialist

AuraOne, Inc.; United States; Remoto; USD 39.000 - 52.000; Part-time

Descrizione del lavoro

AuraOne, Inc. is seeking a remote Video Instruction Following Evaluator to review model outputs and provide structured feedback. You will compare paired responses, assign severity tags, and label content issues according to a versioned rubric.

Responsibilities include documenting failure modes, calibrating scores weekly, and routing ambiguous prompts for rubric updates. This contractor role requires strong attention to detail and the ability to work asynchronously for at least 10 hours per week.

Competenze

• Prior evaluation, annotation, or human-rater experience on video instruction following evaluation.
• Clear written reasoning that names the issue and the rubric clause.
• Strong attention to detail and the ability to flag when a prompt itself is the problem.
• Reliable async availability for at least 10 hours per week.

Mansioni

• Evaluate video instruction following evaluation model outputs against a versioned rubric and assign severity tags for Video Instruction Following 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.

Conoscenze

Model evaluation

Rubric annotation

Severity tagging

Inter-rater calibration

Video instruction following

Computer vision

Spatial reasoning

Video QA

Video

Instruction

Following

Descrizione del lavoro

AuraOne, Inc. is seeking a remote Video Instruction Following Evaluator to review model outputs and provide structured feedback. You will compare paired responses, assign severity tags, and label content issues according to a versioned rubric.

Responsibilities include documenting failure modes, calibrating scores weekly, and routing ambiguous prompts for rubric updates. This contractor role requires strong attention to detail and the ability to work asynchronously for at least 10 hours per week.