Skip to main content

AI Research Intern – Predictive World Model

Summary by AIEngineer.careers

AI Research Intern – Predictive World Model is a AI Research Engineer role (internship). with XPENG. in SANTA CLARA, US. Imported listing (source: feeny.ai). Apply on the employer's site (feeny.ai).

Imported listing (source: feeny.ai) · Apply on feeny.ai

How our listings work

SANTA CLARA · US
—
Internship
JUNIOR
Apply Now

More AI jobs in United States

The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.

Imported job description

Sourced from feeny.ai

XPENG is seeking PhD research interns to develop predictive world models that learn physical-world dynamics from large-scale multimodal data, serving as learned simulators for driving and robotic policies. Interns drive a focused research project end to end using state-of-the-art generative architectures such as diffusion and flow-matching models, video tokenizers, and transformer-based multimodal backbones. Strong results are supported for publication at top-tier venues, with access to real-world multimodal data from XPENG's autonomous fleet and robotics platforms.

Responsibilities

  • Drive a focused research project on predictive world models from problem formulation through architecture design, training, evaluation, and empirical analysis
  • Contribute to multi-view future prediction, shared backbone prediction-and-action architectures, or predictive pre-training for VLA driving performance
  • Extend prediction into multimodal latent spaces spanning 3D scene representations, occupancy, and reward signals
  • Investigate cross-embodiment generalization via unified observation and action representations
  • Build evaluation methodology for representation quality, prediction accuracy, generation fidelity, physical plausibility, and closed-loop policy performance
  • Collaborate with research engineers to move prototypes into scalable training and inference pipelines and publish results

Requirements

  • Currently pursuing a PhD in Engineering, Computer Science, or a related field focused 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
  • Strong foundation in generative modeling and experimental methodology with hands-on experience in PyTorch or JAX
  • Strong Python programming and software design skills including data structures, algorithms, and large-scale data processing
  • Available for a minimum 12-week commitment, working on-site at the Santa Clara office

Nice to Have

  • Hands-on experience with generative models for video or 3D such as diffusion, flow matching, autoregressive video prediction, NeRF, or Gaussian Splatting
  • Experience with world models or learned simulators, including model-based reinforcement learning and VLA models
  • Experience with multimodal foundation models, video tokenizers, or VAEs
  • Prior research internship experience in autonomous driving, robotics, or embodied AI, or open-source contributions

Tech Stack

Computer VisionDiffusion ModelsFlow MatchingGaussian SplattingGenerative ModelsJAXNeRFPythonPyTorchReinforcement LearningTransformersVision-Language-ActionWorld Models
XPENG

XPENG

深圳市 · CN · 19884+ employees

XPENG is a leading Chinese smart electric vehicle (EV) company that designs, develops, manufactures, and markets intelligent EVs. The company focuses on integrating advanced driver-assistance systems, in-car intelligent operating systems, and core vehicle technologies to transform the mobility experience.

Weekly job alert

Get a weekly email when new AI engineering jobs match your filters. Free — confirm your address to start.

Related Jobs