About the role#
NVIDIA Dynamo is an open-source platform focused on efficient, scalable inference for large language and reasoning models in distributed GPU environments. As an intern on the Dynamo project, you will work on distributed AI infrastructure, including Kubernetes serving, disaggregated serving, GPU scheduling, intelligent routing, and distributed KV cache management.
What you'll do#
- Collaborate on the design and development of the Dynamo Kubernetes stack.
- Introduce new features to the Dynamo Python SDK and Dynamo Rust Runtime Core Library by designing, implementing, and optimizing distributed inference components.
- Contribute to the development of disaggregated serving for Dynamo-supported inference engines.
- Improve intelligent routing and KV-cache management subsystems.
- Contribute to open-source repositories, participate in code reviews, and assist with issue triage on GitHub.
What you'll need#
- Current pursuit of a BS, MS, or PhD in Computer Science or an equivalent program.
- Excellent programming and software design skills in Golang, Rust, and/or Python.
- Strong understanding of algorithms and data structures.
- Solid knowledge of RESTful APIs.
- Ability to work in a highly motivated and dedicated manner with a focus on new technologies.
Location & details#
- Location: Santa Clara, California.
- Term: Fall 2026.
- Modality: On-site.
- Employment type: Full-time.
- Compensation: This is a paid internship with an hourly rate range of 20 USD to 71 USD.
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.
