Research Engineer, Post-Training Multimodal

OpenAI is seeking a Research Engineer to work on post-training aspects of multimodal models. You will collaborate with a team of world-class researchers and engineers to develop novel techniques for model optimization, probing, and evaluation. This role will involve designing and implementing complex pipelines for training, fine-tuning, and evaluating large language models, as well as contributing to fundamental research on techniques like reinforcement learning from human feedback (RLHF). You should have strong software engineering skills, an understanding of modern deep learning architectures, and a passion for pushing the boundaries of what's possible with large language models.