Korean AI Evaluator

Job Summary

To support an upcoming project, the contracted Korean AI Evaluator will remotely test and evaluate AI chatbots and language models, providing insights to enhance their response quality while working flexibly on a task-based schedule.

Key responsibilities

• Test and evaluate AI chatbots through structured conversations using assigned goals and prompts
• Engage in voice-based interactions with AI models, recording sessions as part of the evaluation deliverables
• Submit various deliverables, including write-ups, ratings, and recordings, according to project specifications

Required qualifications

• Native or expert-level fluency in Korean, as spoken in South Korea
• Strong English reading, writing, and communication skills
• Hands-on experience using AI models or large language models
• Access to a smartphone, computer, and reliable internet, with comfort in using web-based tools
• Able to pass a language proficiency and technical literacy assessment