Description
The company is hiring a Senior Research Scientist to lead model post-training research, including supervised fine-tuning, RLHF/RLAIF, reward modeling, preference-data design, evaluation suites, and production experiments. The role owns a research area, runs rigorous experiments, partners with data, infrastructure, and engineering teams, and ships improvements into production. Candidates need strong post-training research experience, at least five years of hands-on machine learning research experience, large-scale data-curation and evaluation experience, PyTorch or equivalent expertise, and strong statistical and written-communication skills.
