Portuguese Generalist Evaluator Expert at Mercor

Portuguese AI Evaluator | $12–15/hr | Remote in Brazil

Mercor is seeking native Portuguese speakers with exceptional writing skills to contribute to a high-impact AI research project with a leading lab. This short-term, flexible opportunity is ideal for professionals who combine language mastery, strong critical thinking, and instructional clarity. You'll create bilingual prompt-answer pairs that train and evaluate advanced language models while maintaining cultural authenticity for Brazilian Portuguese speakers.

Key Responsibilities:

• Multilingual Prompt Design: Create detailed prompts in Portuguese and English with multiple constraints, ensuring natural phrasing and real-world relevance for Portuguese-speaking users
• Evaluation Standards: Establish high-level expectations for correct responses in Portuguese consumer contexts and develop comprehensive rubrics accounting for linguistic nuance, tone, and cultural conventions
• Model Testing & Grading: Run prompts through AI models and assess outputs for accuracy, fluency, and cultural fit in Portuguese, comparing results against English benchmarks where needed
• Quality Assurance: Collaborate in QA review processes to ensure prompt tasks and rubrics meet rigorous standards, maintaining consistency across Portuguese-language evaluations

Minimum Qualifications:

• Native-level fluency in Portuguese (written) with strong reading/writing ability in English
• BS or BA from a reputable institution (completed or in progress)
• Strong writing and critical thinking skills
• Ability to work independently and meet deadlines
• Significant familiarity with ChatGPT or similar AI tools
• Based in Brazil or able to reliably produce Brazil-specific, culturally accurate Portuguese

Preferred Qualifications:

• Experience in teaching, research, editing, or academic writing
• Experience creating evaluation criteria, rubrics, or grading guidelines
• Familiarity with LLMs, prompting, or model evaluation

Project Details:

• Commitment: At least 20 hours per week for approximately 2+ months
• Application process includes a 15-minute AI-led interview and 45-minute written assessment
• Structured project environment with clear goals and tools