2 months ago
Beijing, ChinaSenior
Responsibilities
- Develop and optimize reinforcement learning algorithms and infrastructure for large language and multimodal models.
- Enable open-source model support in NVIDIA reinforcement learning and post-training frameworks.
- Collaborate with research and engineering teams to adapt and validate reinforcement learning methods and optimizations on NVIDIA platforms.
- Provide technical guidance to customers integrating NVIDIA reinforcement learning technologies into AI workflows.
- Develop reusable toolchains, experiment management workflows, and technical documentation for internal and customer-facing projects.
Requirements
- MS or PhD in Computer Science, Artificial Intelligence, Mathematics, or a related field.
- At least five years of experience, including research, in reinforcement learning, large language model training, or multimodal learning.
- Proficiency in PyTorch and familiarity with reinforcement learning training frameworks and workflows.
- Strong engineering skills in distributed training, task orchestration, or evaluation pipelines.
- Ability to work independently, conduct exploratory experiments on frontier problems, and contribute to diverse projects.
- Outstanding verbal and written communication skills.
- Preferred experience with RLHF, GRPO, DPO, other LLM alignment and post-training methods, scale-out HPC or cloud architectures, CUDA optimization, GPU performance tuning, agentic AI systems, code generation models, multimodal reinforcement learning, or top-tier publications in reinforcement learning, NLP, or multimodal learning.
Benefits
- Competitive salary and a generous benefits package.
Categories
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.