Job Description

Policy Preference Reward Model Evaluator is a remote review track for evaluating AI outputs in policy review workflows. Reviewers grade citation accuracy, statutory reasoning, and policy adherence; flag risk; and document the corrected analysis so the modeling team can train on it.

Why this role matters

Policy review content is judged on precision. AuraOne uses qualified legal and policy reviewers to grade AI outputs the way a senior associate would — with citations, severity tags, and the corrected reasoning alongside the original.

Responsibilities

• Review AI outputs against current policy review statutes, case law, or policy for Policy Preference Reward Model Evaluator assignments.
• Verify citations, jurisdictions, and dates against authoritative sources.
• Flag risky reasoning, missed exceptions, and policy-adherence gaps with severity tags.
• Capture the corrected analysis or memo paragraph so the modeling team can train on it.
• Adjudicate disputed treatments against published authority or firm policy.
• Maintain reviewer-quality scores in inter-rater calibration cycles.

Qualifications

• Active or recent qualification in policy review or an adjacent practice for Policy Preference Reward Model Evaluator work.
• Hands-on experience drafting, reviewing, or advising on real matters.
• Comfort applying multi-page rubrics consistently across long batches.
• Clear written reasoning that cites authority and names the rule being applied.
• Reliable async availability for at least 10 hours per week.

Example tasks

• Verify the citations in a model's policy review memo and flag any miscites with severity.
• Grade a model's statutory reasoning on a complex fact pattern and rate the analysis.
• Adjudicate a disputed treatment between two reviewers using current authority.
• Audit a 25-row batch for rubric consistency and report drift to the program lead.

Nice to have

• Bar admission or legal-equivalent credential in a relevant jurisdiction.
• Prior experience reviewing AI-assisted legal-research or compliance tooling.
• Bilingual experience for cross-jurisdiction matters.

Skills

• Legal research
• Citation review
• Statutory analysis
• Policy reasoning
• Policy review
• Preference ranking
• RLHF
• Rater calibration
• Policy
• Preference

Work model

Remote — US-eligible. Remote · Independent specialist contractor. Employment type: CONTRACTOR. Applicants must be authorized to work from US.

Compensation

Hourly rate confirmed after the interview process.

Application process

Apply through AuraOne's specialist intake for role-specific routing and review. Final project scope, schedule, and contractor terms are confirmed before placement.

Job Tags

Similar Jobs