Program evaluator [h1.location_city]

Mercor is seeking native

• Korean
• speakers with exceptional writing skills to contribute to a high-impact AI research project with a leading lab. Freelancers will author
• Korean / English
• prompt–golden answer pairs that train and evaluate advanced language models. This is a short-term, flexible opportunity for professionals who combine language mastery, strong critical thinking, and a knack for instructional clarity. Ideal for those who enjoy distilling complex concepts into well-crafted, culturally grounded
• Korean
• text while maintaining technical precision in English.
• ##
• Job Details
• ###
• Multilingual Prompt Design & Optimization :
• Create detailed prompts in Korean and / or English with multiple constraints and instructions, ensuring natural phrasing and real-world relevance for Korean-speaking users. ###
• Define and Document Evaluation Standards :
• Establish high-level expectations for correct responses in Korean consumer contexts, and develop comprehensive rubrics that account for linguistic nuance, tone, and cultural conventions. ###
• Model Testing and Grading (Bilingual) :
• Run prompts through models and assess preliminary outputs for accuracy, fluency, and cultural fit in Korean, comparing results against English where needed. ###
• Benchmarking & Quality Assurance :
• Collaborate in QA review processes to ensure prompt tasks and rubrics meet rigor—maintaining consistency and reliability across Korean-language benchmarks before integration into official evaluations.
• ##
• Minimum Qualifications
• Native-level fluency in Korean (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 tools for personal decision-making, hobbies, or general interests. - Based in
• South Korea
• (or able to reliably produce
• South Korea-specific
• , culturally accurate Korean).
• ##
• 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 (helpful but not required).
• ##
• Application & Onboarding Process
• Complete an AI-led interview (about 15 minutes). - Complete a 45-minute written assessment focused on writing and rubric creation. - If selected, you will be invited to work on the project.
• ##
• More Details About This Role
• Expect to contribute at least 20 hours per week. - Expect a commitment of around 2+ months. - You’ll be working in a structured project environment with clear goals and tools. - We consider all qualified applicants without regard to legally protected characteristics and provide reasonable accommodations upon request.