Content Specialist III | AI Evaluation & Prompting (Fully Remote)

Partner Company; United States; Remote; USD 90,000 - 120,000; Full time

Benefits offered by this job

Health coverage

Remote contract

Job summary

Partner Company is seeking a skilled evaluator to test new AI model versions across diverse topics and evaluate responses against quality standards.

You will write, test, and refine system prompts to influence model behavior and performance, identify and document failures, and provide clear, actionable feedback. This six-month remote contract offers full-time scheduling and comprehensive health coverage.

Qualifications

• 5+ years of professional experience in writing, editing, or a related discipline.
• At least 1 year of hands-on AI experience including prompting or model evaluation.
• Strong analytical judgment, attention to detail, and ability to apply rubrics consistently.

Responsibilities

• Test new AI model versions across diverse topics and evaluate responses against quality standards.
• Write, test, and refine system prompts to influence model behavior and performance.
• Identify and document model failures and provide clear, actionable feedback.

Skills

Writing/editing

AI prompting

Analytical reasoning

Attention to detail

Rubrics-based evaluation

Job description

• Test new AI model versions across diverse topics and evaluate responses against quality standards.
• Write, test, and refine system prompts to influence model behavior and performance.
• Identify and document model failures and provide clear, actionable feedback.

Your Requirements:

• 5+ years of professional experience in writing, editing, or a related discipline.
• At least 1 year of hands-on AI experience including prompting or model evaluation.
• Strong analytical judgment, attention to detail, and ability to apply rubrics consistently.
• 6-month remote contract with full-time schedule and comprehensive health coverage.
• Opportunity to work directly on advanced AI system evaluation and improvement.
• Hands-on exposure to prompt engineering and emerging AI products.

Partner Company

This company specializes in evaluating and improving advanced AI systems through content evaluation and prompt engineering. It operates as a partner company managing applications for this role, focusing on quality and consistency in AI behavior.