Staff AI Engineer: LLM Post-Training & Alignment

A leading crypto exchange is seeking a Machine Learning Engineer specializing in large model post-training and alignment in Hong Kong. The role involves leading the full post-training pipeline for large language models, implementing advanced training paradigms like DPO and GRPO, and optimizing model performance. You will require at least 8 years of industry experience and a strong understanding of reinforcement learning fundamentals. The company offers comprehensive healthcare schemes, wellness allowances, and various team-building programs.

#J-18808-Ljbffr