About this role
基于数据闭环的Agent调优 at NetEase Leihuo (网易雷火). Location: Hangzhou, Zhejiang, China. Role: tuning agents, building evaluations, researching optimization Requirements: Research and production experience in large models or agents; familiar with SFT and RLHF; able to conduct deep research and publish top-tier papers. Category: Research and Development (R&D) Seniority: Senior Level Tools: SFT, RLHF, Reward Model Commitment: Internship Workplace: Onsite Languages: Chinese