About the role#
We are looking for PhD research interns to advance large language models using reinforcement learning. You will join our applied deep learning research team to develop new methods for improving model reasoning, alignment, and reliability. This role focuses on algorithmic research, hands-on experimentation, and rapid prototyping at scale.
What you'll do#
- Develop and prototype reinforcement learning algorithms for large language models.
- Explore methods to improve instruction following, multi-turn interaction, and reasoning.
- Design experiments to evaluate model robustness, hallucination, and task performance.
- Implement research ideas in Python and PyTorch while running experiments on large-scale GPU clusters.
What you'll need#
- Pursuing a PhD in AI, ML, Computer Science, Electrical Engineering, Mathematics, Physics, or a related field.
- Strong background in reinforcement learning and natural language processing.
- Excellent programming skills in Python.
- Experience with deep learning frameworks like PyTorch.
- Comfort with experimental research, debugging models, and working with large-scale training pipelines.
- Bonus points for publications or open-source contributions in RL, LLMs, or alignment, as well as experience with RLHF, RLAIF, policy optimization, or reward modeling.
Location & details#
- Location: Santa Clara, California.
- Term: Fall 2026.
- This is a paid, full-time internship. We do not provide sponsorship for this position.
About NVIDIA
NVIDIA operates as a computer hardware manufacturer based in Santa Clara, California. Founded in 1993, the company focuses on accelerated computing and graphics technology. It produces hardware for markets including artificial intelligence, gaming, and data centers. The organization employs over 50,000 people and maintains a global presence.
How to get in at NVIDIA
Applying early gives you a distinct advantage at NVIDIA because recruiters review applications as they arrive. Intern Insider sends an instant alert the moment a role matching your target is published, so you can apply among the first before the pile grows. Getting your resume in front of a human early is often the difference between a screening call and a rejection. You can use Intern Insider to surface the recruiters behind NVIDIA roles to reach out directly. Asking a recruiter about the role or a referral materially improves your response rates compared to submitting into a general queue. It is a simple way to make your application stand out in a competitive process.
