Scriptwriter

AuraOne, Inc.; United States; Remote; USD 34,000 - 76,000; Part time

Job summary

AuraOne, Inc. is seeking a remote Scriptwriter reviewer to evaluate AI outputs within domain writing workflows. You will assess tone, escalation logic, and stakeholder fit using a structured rubric, flag risks, and document actionable next steps for model training.

You will apply multi-page rubrics across large batches, ensuring clear reasoning that names the applicable policy or workflow. The role requires reliable async availability of 10+ hours per week and strong attention to detail.

Qualifications

• Direct working experience in domain writing on real teams for Scriptwriter work.
• Comfort applying multi-page rubrics consistently across long batches.
• Clear written reasoning that names the policy or workflow 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

• Review AI outputs against current domain writing workflows, playbooks, and firm policy for Scriptwriter assignments.
• Grade tone, escalation logic, and stakeholder fit on a structured rubric.
• Flag operational risk, missed escalations, and policy-adherence gaps with severity tags.
• Capture the right next step so the modeling team can train on it.
• Adjudicate disputed treatments against published playbooks or firm guidance.
• Maintain reviewer-quality scores in inter-rater calibration cycles.

Skills

Operational review

Policy adherence

Workflow judgment

Stakeholder communication

Domain writing

Tools

AI tooling

Job description

Scriptwriter is a remote review track for evaluating AI outputs across domain writing workflows. Reviewers grade workflow correctness, policy adherence, and stakeholder fit; flag operational risk; and document the right next step so the modeling team can train on it.

Why this role matters

Domain writing AI has to fit into an actual day at work. AuraOne uses experienced operators to grade outputs the way a senior peer would — checking workflow, policy, and the unwritten rules that decide whether a task actually gets done.

Responsibilities

• Review AI outputs against current domain writing workflows, playbooks, and firm policy for Scriptwriter assignments.
• Grade tone, escalation logic, and stakeholder fit on a structured rubric.
• Flag operational risk, missed escalations, and policy-adherence gaps with severity tags.
• Capture the right next step so the modeling team can train on it.
• Adjudicate disputed treatments against published playbooks or firm guidance.
• Maintain reviewer-quality scores in inter-rater calibration cycles.

Qualifications

• Direct working experience in domain writing on real teams for Scriptwriter work.
• Comfort applying multi-page rubrics consistently across long batches.
• Clear written reasoning that names the policy or workflow 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.

Example tasks

• Grade a model's response to a real domain writing ticket and rate workflow, tone, and escalation.
• Flag a missed escalation with the right severity tag and corrected next step.
• Adjudicate a disputed playbook call between two reviewers using firm guidance.
• Audit a 25-row batch for rubric consistency and report drift to the program lead.

Nice to have

• Prior experience training, calibrating, or QA-ing operations teams.
• Familiarity with AI-assisted workflow tooling and its failure modes.
• Bilingual experience for cross-region operations.

Skills

• Operational review
• Policy adherence
• Workflow judgment
• Stakeholder communication
• Domain writing

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.

Direct working experience in domain writing on real teams for Scriptwriter work.

Comfort applying multi-page rubrics consistently across long batches.

Clear written reasoning that names the policy or workflow 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.