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.


This internship will focus on algorithmic research at the intersection of reinforcement learning and large language models. You will design, implement, and evaluate new RL-based methods for improving LLM behavior, with a strong emphasis on hands-on experimentation and rapid prototyping at scale.


What you will be doing:
+ 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 beha...