Research Scientist, Generative AI for Graphics and Gaming

NVIDIA•Us, CA

About The Position

We are now seeking a Research Scientist in Generative AI for Graphics and Gaming ! NVIDIA is seeking world-class deep learning researchers to build the next generation of AI for graphics and gaming—from neural rendering and real-time image/video generation to world models, AI-driven characters, and LLM-powered game experiences. Join our Applied Deep Learning Research team, renowned for revolutionizing real-time graphics with powerful AI technologies like DLSS. You’ll have access to abundant GPU compute to explore ambitious ideas and train large models at scale. We prioritize step-change research that delivers undeniable user experience improvements, not incremental benchmark gains. You’ll work across multiple organizations at NVIDIA to drive fundamental AI research all the way into shipping products used by millions of players. Our team pushes the limits of real-time graphics and interactive storytelling experiences using the latest advances in AI. If you’re passionate about deep learning, real-time graphics, and delivering transformative technology directly into games and graphics applications, you’ll be a great fit. In this role, you will conduct cutting-edge research, train advanced models, prototype in real-time engines, and work with product, driver, and hardware teams to bring your ideas to market.

Requirements

MS or PhD in Computer Science/Engineering, Electrical Engineering, Applied Mathematics, or a related field (or equivalent experience).
3+ years of deep learning experience in image/video generation, graphics, computer vision, or related fields, with a solid understanding of core DL fundamentals.
Extensive hands-on experience training large models on multi-GPU clusters (hundreds to thousands of GPUs), building robust distributed training pipelines and debugging at scale, with strong proficiency in PyTorch required; familiarity with GPU architecture, CUDA abstractions, and efficiency techniques (e.g., distillation, pruning, low-precision training/inference) is a plus.
Proven track record of impactful research and shipped ideas (e.g., leading publications, production features, or widely used tools), and strong communication and collaboration skills in cross-functional teams.

Nice To Haves

Background in graphics—such as rendering pipelines or game engines—and experience with generative models, neural rendering, or reconstruction is a plus.

Responsibilities

Research and develop AI models that improve real-time graphics quality, robustness, performance, and latency, and enable new interactive experiences such as world models, LLM-driven gameplay, and AI-driven characters.
Design and run large-scale pre-training and post-training for foundation models for graphics and gaming, using NVIDIA’s GPU infrastructure for experimentation and iteration.
Build and own data pipelines and datasets for foundation models and large-scale training, spanning synthetic data, in-engine captures, and real-world content.
Develop and prototype models for real-time image, video, and 3D content generation in modern game engines and graphics frameworks, and create demos that clearly showcase player-visible benefits.
Stay current on AI and graphics research and work with product, driver, hardware, engine, and platform teams to turn promising ideas into shipping, user-visible features.