💼 About This Role

You'll design complex evaluation frameworks for an AI benchmark project, creating prompts, rubrics, and training data for government and policy domains. Your work directly improves AI accuracy in public administration tasks. This freelance role offers autonomous project work with flexible remote scheduling.

🎯 What You'll Do

• Create realistic prompts for AI model evaluation in government contexts.
• Develop clear, well-structured rubrics with non-ambiguous scoring criteria.
• Generate clean, reliable benchmark evaluation data for model training.
• Fact-check tasks and rubrics against real-world legislative standards.

📋 Requirements

• 3+ years of professional experience in public administration or regulatory compliance.
• Strong writing skills for crafting realistic civic task scenarios.
• Proficiency in rubric generation with objective, non-ambiguous criteria.
• Meticulous attention to detail for fact-checking policy documents.

✨ Nice to Have

• Experience with AI model evaluation or prompt engineering.
• Background in legislative affairs or civic planning.
• Familiarity with bureaucratic terminology and public sector deliverables.

🎁 Benefits & Perks

• 🏖️ Remote work with flexible schedule.
• 💰 Pay rate of $10-$30 per hour based on experience.

📨 Hiring Process

Estimated timeline: 2-3 weeks · AI estimate

1. 1Application Review· 1 week
2. 2Skills Assessment· 1 week
3. 3Offer· 1 week

🚩 Heads Up

• Freelance role with no benefits, health insurance, or PTO.
• Wide pay range ($10-$30/hr) with ambiguity on rate determination.