LLM Reinforcement Learning Framework Engineer
NVIDIA
Shanghai
Workplace: OnsiteFull timeFunction: Education & TrainingExperience: 3+ yearsEducation: bachelorsSkills: ["Python","PyTorch","Multi-GPU","Distributed training","LLM","NeMo RL","Megatron-LM","DeepSpeed","VLLM","TensorRT-LLM","Asyncio","Ray","Torch.distributed"]Develop and deploy reinforcement learning methods for LLM post-training to improve reasoning and alignment, integrating RL components into the LLM training/serving stack. Conduct experiments and debugging workflows to ensure robustness and scalability in production, collaborating with engineers and researchers across teams to push state-of-the-art AI capabilities.
