Remote Drone Perception Evaluation Specialist

AuraOne, Inc.; United States; Remoto; USD 21.000 - 41.000; Tempo pieno

Descrizione del lavoro

AuraOne, Inc. is seeking a Drone Perception Task Evaluator to remotely review drone perception task evaluation prompts and responses against AuraOne's quality rubric.

You will compare paired outputs, annotate edge cases, and provide structured feedback for retraining the modeling team. The role emphasizes clear reasoning, attention to detail, and scheduling flexibility with async work expected for at least 10 hours per week.

Competenze

• Prior evaluation, annotation, or human-rater experience on drone perception task evaluation or adjacent content for Drone Perception Task Evaluator work.
• Comfort applying multi-page rubrics consistently across long batches.
• Clear written reasoning that names the issue and the rubric clause being applied.
• 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 drone perception task evaluation model outputs against a versioned rubric and assign severity tags for Drone Perception Task 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 output evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

Drone Perception Task evaluation

Robotics evaluation

Embodied AI

Safety review

Drone

Perception

Descrizione del lavoro

AuraOne, Inc. is seeking a Drone Perception Task Evaluator to remotely review drone perception task evaluation prompts and responses against AuraOne's quality rubric.

You will compare paired outputs, annotate edge cases, and provide structured feedback for retraining the modeling team. The role emphasizes clear reasoning, attention to detail, and scheduling flexibility with async work expected for at least 10 hours per week.