ML Engineer: World Models & Generative AI (Equity)

Xpeng Inc.; Santa Clara, Northern (CA, KY); Hybrid; USD 175,000 - 296,000; Full time

Benefits offered by this job

Competitive compensation package

Snacks, lunches, dinners, and fun δρα

Job summary

XPENG is seeking Machine Learning Engineers specializing in generative modeling and large-scale deep learning systems. You will research, implement, and evaluate world models predicting how scenes evolve from multimodal driving and robotics data, using diffusion, flow-matching, video tokenizers, and transformer-based backbones.

You will collaborate with experts in CV, generative AI, and AI systems, training on data from our autonomous fleet and robotics platforms.

Qualifications

• MS or PhD in Engineering or Computer Science, or equivalent experience.
• Strong experience in applied deep learning including model architecture design, large-scale model training, data curation and empirical analysis.
• 1-3 years+ with DL frameworks such as PyTorch and distributed training (FSDP, DeepSpeed, Megatron-style).
• Strong Python programming experience with software design skills.
• Solid understanding of data structures, algorithms, and large-scale data processing.

Responsibilities

• Research and develop predictive world models forecasting future states from multimodal data.
• Develop high-quality multi-view future prediction and generation for action-conditioned rollouts and unconditioned forecasts.
• Design architectures where a shared backbone predicts futures and generates trajectories or actions for policy learning.
• Extend prediction into a 3D multimodal latent space using Gaussian Splatting with occupancy and reward signals.
• Advance cross-embodiment generalization across vehicles and robots with few-shot data.
• Define and build evaluation methodologies for predictive world models and feed results back into training.

Skills

Deep Learning

Python Programming

Distributed Training

Research & Analysis

Multimodal Data

Education

MS or PhD

Tools

PyTorch

DeepSpeed

Megatron

FSDP

Job description

XPENG is seeking Machine Learning Engineers specializing in generative modeling and large-scale deep learning systems. You will research, implement, and evaluate world models predicting how scenes evolve from multimodal driving and robotics data, using diffusion, flow-matching, video tokenizers, and transformer-based backbones.

You will collaborate with experts in CV, generative AI, and AI systems, training on data from our autonomous fleet and robotics platforms.