PhD Researcher Intern, World Foundation Models
Salary not listed • Korea, Seoul • Internship
Posted 2d ago
Job Location
Korea, Seoul
Tech Stack
Remote Work Policy
On-site
Employment Type
Internship
Categories
AI Research Engineer
About the job
NVIDIA is seeking a PhD research intern to advance world foundation models within NVIDIA Cosmos for Physical AI. This research will explore new model architectures, training objectives, and efficient training and inference for multimodal generation and action-conditioned prediction, with a focus on physical plausibility, spatial and temporal consistency, and the modeling of human appearance, motion, and interactions. The intern will collaborate with NVIDIA researchers and engineers to define and pursue a focused research project, develop new methods, and demonstrate measurable improvements through rigorous experimentation, with projects tailored to team priorities and the intern's research strengths.
Responsibilities
- Research and develop model architectures, training objectives, and learning algorithms for video generation and world modeling, including diffusion or flow-matching approaches, multimodal conditioning, and spatial and temporal representations.
- Design controlled experiments and ablation studies to diagnose model behavior, identify failure modes, and validate improvements using quantitative benchmarks and qualitative evaluation.
- Explore training and inference efficiency through architectural changes, distillation, model compression, or other optimization techniques.
- Develop data curation and evaluation workflows, including model-assisted filtering, annotation, and quality assessment, and measure their impact on model performance.
- Collaborate with research and engineering teams and share findings through reproducible implementations, technical reports, and presentations.
Requirements
- Currently pursuing a PhD in Computer Science, Computer Graphics, Computer Engineering, Robotics, or a closely related field.
- Research experience in generative modeling, computer vision, video understanding or generation, multi-modal learning, 3D vision, or robotics.
- Strong proficiency in Python and PyTorch, demonstrated through research implementations or substantial projects.
- Hands-on experience implementing, training or fine-tuning, and evaluating deep learning models.
- Ability to formulate research questions, design rigorous experiments, analyze results, and communicate findings clearly.
- Comfortable working in Linux and using standard development practices for ML research, including version control, testing, and experiment reproducibility.
Benefits
- Highly competitive salaries
- Comprehensive benefits package