AI Research Intern – Predictive World Model

XPENG is a leading smart technology company at the forefront of innovation, integrating advanced AI and autonomous driving technologies into its vehicles, including electric vehicles (EVs), electric vertical take-off and landing (eVTOL) aircraft, and robotics. With a strong focus on intelligent mobility, XPENG is dedicated to reshaping the future of transportation through cutting-edge R&D in AI, machine learning, and smart connectivity.

We are seeking PhD research interns with strong expertise in generative modeling and a demonstrated record of original research. In this role, you will work alongside our research team to develop world models that learn the dynamics of the physical world from large-scale multimodal data — predicting how a scene evolves under an agent's actions, and serving as a learned simulator for training and evaluating driving and robotic policies. You will work with state-of-the-art generative architectures, including diffusion and flow-matching models, video tokenizers, and transformer-based multimodal backbones, with access to vast amounts of real-world multimodal data from our autonomous fleet and robotics platforms. Interns are expected to drive a focused research project end to end, and strong results are supported for publication at top-tier venues.

Job Responsibilities:

• Drive a focused research project on predictive world models, spanning problem formulation, architecture design, training, evaluation, and empirical analysis, in close collaboration with a mentor and the broader research team.
• Contribute to one or more of the following directions: high-quality multi-view future prediction and generation, supporting both action-conditioned rollouts and formulations that forecast the future without explicit action conditioning; architectures in which a shared backbone both predicts the future and produces trajectories or actions; predictive pre-training to improve Vision-Language-Action (VLA) driving performance.
• Extend prediction beyond 2D pixels into a shared multimodal latent space that spans 3D scene representations such as Gaussian Splatting, together with occupancy and reward signals, so that a single model can support simulation, evaluation, and policy training.
• Investigate cross-embodiment generalization through unified observation and action representations and embodiment-conditioning mechanisms, so that a single world model transfers across vehicles, robots, and sensor configurations with only few-shot data.
• Build evaluation methodology for predictive world models, spanning representation quality, prediction accuracy, generation fidelity, physical plausibility, long-horizon rollout consistency, and closed-loop policy performance.
• Collaborate with research engineers to move research prototypes into scalable training and inference pipelines, and publish and open-source results where appropriate.

Minimum Skill Requirements:

• Currently pursuing a PhD in Engineering, Computer Science, or a related field, with a focus on Deep Learning, Computer Vision, or Generative Models.
• First-author publications at top-tier venues such as CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, CoRL, RSS, or SIGGRAPH. Work under submission may be presented as an arXiv preprint.
• Strong, up-to-date foundation in generative modeling and experimental methodology, with hands-on experience building, training, fine-tuning, and evaluating models in PyTorch or JAX.
• Strong Python programming and software design skills, with a solid understanding of data structures, algorithms, code optimization, and large-scale data processing.
• Available to commit to a minimum of 12 weeks and work on-site at our Santa Clara office.

Preferred Skill Requirements:

• Hands-on experience with generative models for video or 3D, such as diffusion, flow matching, autoregressive video prediction, or neural scene representations including NeRF and Gaussian Splatting.
• Experience with world models or learned simulators for decision making, including model-based reinforcement learning and Vision-Language-Action (VLA) models.
• Experience with multimodal foundation models and video tokenizers or VAEs, including pretraining or adapting large pretrained backbones.
• Prior research internship experience in autonomous driving, robotics, or embodied AI, or contributions to widely used open-source projects.

What do we provide:

• A fun, supportive and engaging environment.
• Infrastructures and computational resources to support your work.
• Opportunity to work on cutting edge technologies with the top talents in the field.
• Opportunity to make significant impact on the transportation revolution by the means of advancing autonomous driving.
• Competitive compensation package.
• Snacks, lunches, dinners, and fun activities.

We are an Equal Opportunity Employer. It is our policy to provide equal employment opportunities to all qualified persons without regard to race, age, color, sex, sexual orientation, religion, national origin, disability, veteran status or marital status or any other prescribed category set forth in federal or state regulations.