Korean-Speaking AI Evaluation Specialist

📋 Description

• • Korean-Speaking AI Evaluation Specialist role focused on assessing and improving the quality of AI-generated responses in Korean, ensuring accuracy, relevance, and cultural appropriateness without performing translation.
• • Day-to-day responsibilities include evaluating and comparing AI-generated responses in Korean, conducting side-by-side analysis of outputs from different AI systems, assessing responses for accuracy, relevance, clarity, and instruction-following, identifying nuances in meaning, tone, and cultural context, applying structured annotation guidelines consistently, and working with datasets of real user queries.
• • Blueprint is a technology solutions firm headquartered in Bellevue, Washington, with a strong U.S. presence, dedicated to solving complex problems by bridging strategy and execution through technology, powered by diverse, experienced teams across industries.
• • In this role, you will develop expertise in AI evaluation, linguistic analysis, and structured annotation while contributing to cutting-edge AI systems, gaining hands-on experience with real-world AI performance data, and growing your career in a supportive, innovative environment that values diverse perspectives and professional development.