Generalist – English & French (LLM Evaluator)

Why This Role Exists

Mercor partners with leading AI teams to improve the quality, usefulness, and reliability of general-purpose conversational AI systems.

This project focuses on evaluating and improving general chat behavior in large language models (LLMs). You will assess AI-generated responses across diverse topics and provide structured human feedback to ensure outputs are accurate, well-reasoned, and aligned with real-world expectations.

What You’ll Do

• Evaluate LLM-generated responses for clarity, correctness, and completeness.
• Conduct fact-checking using trusted public sources and verification tools.
• Annotate strengths, weaknesses, and factual inaccuracies.
• Assess reasoning quality, tone, and conversational alignment.
• Ensure outputs comply with system guidelines and expected behavior.
• Apply consistent annotations using structured taxonomies and evaluation rubrics.

Who You Are

• Bachelor’s degree holder.
• Native French speaker or ILR 5 / C2 proficiency.
• Fluent in English.
• Experienced user of large language models (LLMs).
• Strong writing skills with ability to articulate nuanced feedback.
• Highly detail-oriented and analytical.
• Comfortable working across diverse domains and topics.
• Strong college-level mathematics skills.

Nice-to-Have

• Experience with RLHF, model evaluation, or annotation workflows.
• Experience comparing multiple outputs and making fine-grained qualitative judgments.
• Familiarity with evaluation rubrics and benchmarking systems.
• Background in research, analytics, linguistics, or engineering.

What Success Looks Like

• You consistently identify factual inaccuracies and reasoning gaps.
• Your evaluation artifacts are clear, consistent, and reproducible.
• Your feedback leads to measurable improvements in AI response quality.
• AI systems improve before public deployment due to your evaluations.

Contract & Payment

• Independent contractor engagement.
• Fully remote with flexible schedule.
• Weekly payments via Stripe or Wise.
• Geography restricted to Europe, Canada (Quebec), and USA.
• $36.16 per hour.

About Mercor

Mercor partners with leading AI labs and enterprises to train frontier models using human expertise. Contributors collaborate with researchers to improve advanced AI systems used globally.