Deep Learning Solution Architect - RL and Post-training at NVIDIA

NVIDIA is seeking a Reinforcement Learning Engineer to develop and optimize reinforcement learning algorithms and infrastructure for large language models and multimodal models. The role involves enabling open-source model support, adapting RL methods for NVIDIA platforms, collaborating with research and engineering teams, guiding customer integrations, and maintaining toolchains and documentation. Candidates need a master’s or PhD in a relevant field, at least five years of experience in reinforcement learning, large language model training, or multimodal learning, and proficiency with PyTorch, distributed training, and evaluation pipelines.