governor_pump
Evaluate a prompt on how natural it sounds and record the failure buckets in the response generated by 4 different models to the prompt.
Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
No subject matter listed
Actively engaged with Scale AI from July 2024 to June 2025, working over 40 hours per week with an average review score above 4.5. Consistently recognized by peers and managers for punctuality, localization work, and red teaming performance.
Evaluate a prompt on how natural it sounds and record the failure buckets in the response generated by 4 different models to the prompt.
Carried out the localization of English prompts and responses to suit Korean cultural context.
Evaluated and labeled potentially harmful or biased outputs from AI models.
B.A. in English Language and Literature (Expected Feb 2026), Department of English Language and Literature
Studied Psychology, [Chung-buk National University], 2010–2013 (no degree), Psychology
AI trainer
Development Manager