Remote HR Operations AI Evaluator & Rubric Reviewer

AI Trainer Jobs; United States; Remote; USD 28,000 - 55,000; Part time

Job summary

AI Trainer Jobs is seeking a remote Human Resources Operations AI Evaluator contractor to review evaluation prompts and model outputs against a versioned rubric. You will label edge cases, provide structured feedback, and help retrain the modeling team.

Responsibilities include comparing responses, selecting stronger answers with reasoning, tagging content per policy, and flagging prompts for rubric updates. Requires strong attention to detail and reliable async availability for 10+ hours weekly.

Qualifications

• Prior evaluation, annotation, or human-rater experience in HR AI evaluation.
• Ability to apply multi-page rubrics consistently across long batches.
• Clear written reasoning naming the issue and rubric clause.
• Strong attention to detail and flag prompts when necessary.
• Reliable async availability for at least 10 hours per week.
• Background in linguistics, content moderation, or trust & safety review.
• Familiarity with inter-rater agreement metrics.
• Domain expertise to spot errors automated checks miss.

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 tags.
• Capture ambiguous prompts and route to program team for rubric updates.
• Audit batches for rubric consistency and report drift.

Skills

Evaluation experience

Rubric application

Written reasoning

Attention to detail

Async availability

Linguistics background

Inter-rater metrics

Domain expertise

Job description

AI Trainer Jobs is seeking a remote Human Resources Operations AI Evaluator contractor to review evaluation prompts and model outputs against a versioned rubric. You will label edge cases, provide structured feedback, and help retrain the modeling team.

Responsibilities include comparing responses, selecting stronger answers with reasoning, tagging content per policy, and flagging prompts for rubric updates. Requires strong attention to detail and reliable async availability for 10+ hours weekly.