Bilingual German Generalist Evaluator Expert — Mercor

Mercor is seeking native German speakers with exceptional writing skills for a high-impact AI research project with a leading lab. You’ll author German/English prompt-golden answer pairs that train and evaluate advanced language models.

What you’ll do

• Create detailed prompts in German and English with multiple constraints, ensuring natural phrasing and real-world relevance
• Define and document evaluation standards and comprehensive rubrics for cultural and linguistic nuance
• Test models and grade outputs for accuracy, fluency, and cultural fit
• Collaborate in QA review processes for consistency across benchmarks

What they’re looking for

• Native-level fluency in German (written) with strong English reading/writing
• BS or BA from a reputable institution (completed or in progress)
• Strong writing and critical thinking skills
• Familiarity with ChatGPT or similar LLM tools
• Nice to have: teaching, research, editing experience; rubric/evaluation design

Compensation

• Pay: $25-$30/hour
• Type: Hourly contract, 20+ hours/week, 2-4 months commitment
• Location: Remote
• Flexible schedule
• Weekly payments via Stripe or Wise

How to apply

Complete an AI-led interview (~15 minutes). If approved, complete a paid assessment. Then get invited to the project.