AI Translation Evaluator (Korean-English)

TL;DR

AI Translation Evaluator (Korean-English): Evaluating context-dependent translations produced by AI chatbots with an accent on MQM error annotation and adherence to user-specified requirements. Focus on verifying rubric items for relevance and ensuring high-quality, accurate translation outputs for complex multilingual systems.

Location: Remote (Global)

Company

hirify.global is a community-driven platform providing project-based opportunities for language specialists and data evaluators to improve AI systems.

What you will do

• Review conversation histories and translation requests with specific contextual instructions.
• Apply MQM error annotations with appropriate categories and severity levels.
• Verify auto-generated rubric items for relevance and accuracy.
• Evaluate rubric items as Pass or Fail based on user requirements.
• Provide consistent ratings according to project guidelines.
• Complete assigned tasks within established timelines.

Requirements

• Native Korean speaker with a strong command of English.
• Professional background as a language specialist, translator, or holder of a Master's Degree in a language-related field.
• Keen attention to detail.
• Access to a stable internet connection and a computer.

Culture & Benefits

• Flexible, project-based work as an independent contractor.
• Opportunity to contribute to the development of advanced AI translation systems.
• Remote work environment with global accessibility.