About the job
We are looking for PhD research interns excited to advance the next generation of large language models through reinforcement learning. Our applied deep learning research team at NVIDIA has helped pioneer projects such as Megatron, MT-NLG, and DLSS. We build state-of-the-art foundation models and develop new methods to improve their reasoning, alignment, reliability, and ability to solve real-world tasks.
Responsibilities
Develop and prototype reinforcement learning algorithms for large language models
Explore methods for improving reasoning, alignment, instruction following, and multi-turn interaction
Design experiments to evaluate model behavior, robustness, hallucination, and task performance
Implement research ideas in Python and PyTorch, and run experiments on large-scale GPU clusters
Qualifications
Minimum
Pursuing a PhD in AI, ML, CS, CE, EE, Math, Physics, or a related field
Strong background in reinforcement learning and natural language processing
Excellent programming skills, especially in Python
Experience with deep learning frameworks such as PyTorch
Comfort with experimental research, debugging models, and working with large-scale training pipelines
Preferred
Publications or open-source contributions in RL, LLMs, alignment, reasoning, or post-training
Experience with RLHF, RLAIF, policy optimization, reward modeling, or agentic LLM systems
Strong intuition for both algorithms and large-scale implementation