About the job
Core
Establish qualitative evaluation metrics and test sets for AI agents, conduct usability testing to identify improvements, and generate Korean dialogue data for model training.
Role type
AI agent evaluation specialist (Korean NLP)
Builds
Evaluation metrics, test sets, usability reports, and training data for AI agents
Domain
Artificial Intelligence / Natural Language Processing (Korean)
Deliverable
production ML models
Required skills
Korean language proficiency, creative expression, attention to detail, document creation, communication, interest in AI and language models
Preferred skills
AI agent evaluation experience, AI agent generation/usage experience, data labeling experience, NLP project experience
Technologies
Word, Excel
Responsibilities
Establish evaluation metrics and test sets for AI agents, conduct usability testing and identify improvement areas, perform ideation for AI services, create and evaluate tools for agents, write guides for agent usage, generate Korean dialogue text data for model training, perform various Korean NLP tasks
Seniority
Mid-level, hands-on IC