Description
Liquid AI is hiring an ML Scientist focused on post-training to improve the capabilities and behavior of its foundation models for Japan and the global market. The role owns the full experimental loop, including supervised fine-tuning, preference optimization, reinforcement learning, distillation, data curation, evaluation, error analysis, and implementation of reliable training and evaluation pipelines. It is primarily remote for candidates based in Japan, with occasional Tokyo, United States, and Japan travel, flexible working hours, and standard benefits for employees in Japan.
