People Ops Evaluator - Frontier Model Review (Remote)

AI Trainer Jobs; United States; Remote; USD 110,000 - 165,000; Full time

Job summary

AI Trainer Jobs is seeking a remote contractor to evaluate people ops / recruiting prompts and responses against a evolving quality rubric. You will compare model outputs, label edge cases, and provide structured feedback for retraining.

Responsibilities include evaluating rubric-compliance, selecting stronger answers with rationale, and annotating issues like hallucinations or unsafe content. Strong written reasoning and 10+ hours weekly async availability are required.

Qualifications

• Prior evaluation, annotation, or human-rater experience on people ops / recruiting evaluation or adjacent content for People ops / recruiting 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.

Responsibilities

• Evaluate people ops / recruiting evaluation model outputs against a versioned rubric and assign severity tags.
• 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.

Skills

Evaluation experience

Annotation experience

Inter-rater calibration

Written reasoning

Async availability

Tools

Rubric-based annotation

Job description

AI Trainer Jobs is seeking a remote contractor to evaluate people ops / recruiting prompts and responses against a evolving quality rubric. You will compare model outputs, label edge cases, and provide structured feedback for retraining.

Responsibilities include evaluating rubric-compliance, selecting stronger answers with rationale, and annotating issues like hallucinations or unsafe content. Strong written reasoning and 10+ hours weekly async availability are required.