Bilingual AI Trainer (Mandarin + English)
OtherTextRLHF
As a Bilingual AI Trainer, I performed prompt engineering and model evaluations in both Mandarin and English. My responsibilities included developing scoring rubrics and applying reinforcement learning from human feedback to improve LLMs. I helped enhance model response accuracy and relevance in various subdomains. • Conducted prompt engineering and testing for LLMs in Chinese • Developed detailed scoring rubrics for reproducible model assessments • Applied RLHF techniques to train and optimize LLMs • Improved accuracy and relevance of model responses through iterative feedback
As a Bilingual AI Trainer, I performed prompt engineering and model evaluations in both Mandarin and English. My responsibilities included developing scoring rubrics and applying reinforcement learning from human feedback to improve LLMs. I helped enhance model response accuracy and relevance in various subdomains. • Conducted prompt engineering and testing for LLMs in Chinese • Developed detailed scoring rubrics for reproducible model assessments • Applied RLHF techniques to train and optimize LLMs • Improved accuracy and relevance of model responses through iterative feedback
2025 - 2026