Bilingual AI Evaluator Expert (French) at Mercor

Bilingual AI Evaluator (French–English) | $50/hr | Worldwide Remote

Mercor is looking for Internet-Native Bilingual Evaluator Experts fluent in both French and English to support cutting-edge AI research in multilingual communication, internet culture, and real-world language use. This is a flexible, part-time remote role (10–20 hrs/week) ideal for individuals deeply embedded in both French- and English-language online communities.

Key Responsibilities

• Evaluate Internet-Native Communication: Analyse content from French- and English-speaking online communities; assess AI outputs for linguistic accuracy, cultural relevance, and internet authenticity; identify issues with slang, memes, sarcasm, and code-switching.
• Develop Evaluation Standards: Build rubrics for bilingual internet communication, define culturally appropriate language expectations, and document linguistic and cultural edge cases.
• Model Testing & Feedback: Test language models using real-world bilingual prompts in both English and French, and provide detailed, actionable feedback to improve AI performance.
• Quality Assurance: Participate in QA reviews and benchmark creation, ensuring consistency across evaluators and datasets.

Minimum Qualifications

• Native or near-native fluency in French; professional fluency in English
• Strong familiarity with online communities in France, Québec, Belgium, Switzerland, or other French-speaking regions
• Active participation in internet culture across both languages
• Strong writing, analytical, and critical thinking skills
• Availability to commit 10–20 hours per week

Preferred Qualifications

• Background in linguistics, translation, localisation, social media, journalism, humanities, or AI evaluation
• Familiarity with differences between European French, Québec French, and other French varieties
• Experience evaluating online content and internet-native communication
• Interest in AI and multilingual language technologies