Senior Deep Learning Engineer, 4D Foundation Model

NVIDIA is seeking a Senior Deep Learning Engineer to create the next generation of 4D world models. You will develop and train models that reconstruct and interpret dynamic environments from multi-camera video and other sensor observations.

These models will represent geometry, appearance, semantics, objects, motion, and scene dynamics. Your work will turn real-world captures into high-fidelity, simulation-ready environments for autonomous vehicles and Physical AI. You will partner with researchers and engineers in reconstruction, simulation, perception, mapping, and large-scale machine learning.

Responsibilities:

• Develop, train, and evaluate models for accurate, temporally consistent reconstruction of dynamic scenes.
• Create architectures for Gaussian prediction, neural rendering, 3D and 4D reconstruction, object-centric representations, and mapping.
• Model geometry, appearance, semantics, motion, and interactions for realistic, controllable simulation environments.
• Explore diffusion, flow-based, and video-generation methods for novel views, scene completion, temporal prediction, and world generation.
• Scale data and distributed training pipelines for multi-camera video, vehicle poses, perception signals, and other sensor data.
• Build visualization and analysis tools that reveal model behavior and guide measurable improvements.
• Integrate trained models into simulation workflows with production teams, improving reliability and efficiency for downstream applications.

Requirements:

• Five or more years of relevant experience and a BS, MS, or PhD in a related technical field, or equivalent practical experience.
• Proficiency in Python and experience developing and training models with PyTorch or a comparable framework.
• A foundation in deep learning, computer vision, 3D geometry, multi-view geometry, neural rendering, or generative modeling.
• Experience training and evaluating models with large image, video, 3D, or multimodal datasets.
• Ability to work with camera models, calibration, coordinate systems, geometry, motion, uncertainty, and temporal consistency.
• Experience improving models for noisy data, dynamic objects, occlusions, incomplete observations, and uncommon scenarios.
• A systematic approach to debugging, metrics, controlled experiments, and model failure analysis.
• Clear communication and a collaborative approach across research and production engineering teams.

Preferred Qualifications:

• Gaussian splatting, feed-forward 3D reconstruction, NeRFs, differentiable rendering, neural scene representations, or dynamic reconstruction.
• Diffusion models, flow matching, video generation, world models, novel-view synthesis, or generative simulation.
• Machine learning for autonomous driving, robotics, simulation, synthetic-data generation, or other Physical AI applications.
• Distributed training across GPUs or nodes, CUDA optimization, or GPU profiling.
• Publications, open-source contributions, or production results in related fields.