Computer graphics is undergoing its most significant transformation since the invention of the GPU. Generative AI for real-time graphics represents the convergence of foundation models and traditional rendering, opening unprecedented possibilities for visual experiences that were once thought impossible. At NVIDIA, we're not just observing this revolution—we're leading it. Our team sits at the epicenter of this transformation, where pioneering research meets world-changing products used by millions of developers and creators worldwide. Through innovations like Slang—our open-source language and compiler for portable real-time graphics programming—we're enabling developers to seamlessly integrate AI-powered visual generation into graphics workloads, continuously pushing the boundaries of what's possible when generative AI meets real-time rendering.

We're looking for an outstanding PhD student to join our team as a research intern and invent the future of visual computing. Our internships offer an exceptional opportunity to work with access to our in-house compute resources with the latest hardware, and the brightest minds in graphics and AI. We're seeking strategic, ambitious, hard-working, and creative individuals who are passionate about helping us tackle challenges no one else can solve. Does this sound like you? If you're passionate about pushing boundaries and want to impact the future of visual computing, come join us!

‍

‍

What you will be doing:

• Design and implement generative AI algorithms that push the boundaries of real-time graphics and visual content creation
• Develop text-to-image and text-to-video foundation models optimized for interactive graphics applications
• Integrate breakthrough diffusion models and transformer architectures with traditional graphics pipelines to create innovative products
• Pioneer AI-powered content generation techniques for real-time rendering and simulation
• Collaborate with world-class researchers, engineers, and external research partners
• Deliverable results include prototypes, patents, products, and/or publishing original research at top-tier conferences

‍

‍

What we need to see:

• Must be actively enrolled in a university pursuing a PhD degree in Computer Science, Electrical Engineering, Machine Learning, or related field for the entire duration of the internship
• Strong programming skills in Python, C++, CUDA and deep learning frameworks (PyTorch, JAX, TensorFlow)
• Strong research background with publications at top conferences (SIGGRAPH, NeurIPS, ICML, ICCV, CVPR, etc.)
• Excellent communication and collaboration skills
• Experience with large-scale model training and deployment is a plus

‍

‍

Research areas of focus:

We're looking for candidates with research experience in at least one of the following areas:

• Diffusion Models for Image/Video Generation
• Text-to-Image/Video Foundation Models
• Multimodal Vision-Language Models
• Neural Radiance Fields (NeRFs) and 3D Generation
• Real-Time Generative AI and Optimization
• Computer Vision for Graphics Applications
• AI-Powered Content Creation and Synthesis
• Transformer Architectures for Visual Data
• Physics-Based Simulation with AI
• Synthetic Data Generation for Graphics

‍

Applications will be accepted until December 6, 2025.

‍