Senior Staff Machine Learning Engineer – Autonomous Driving Foundation Models

The role

Lead the design of end-to-end Vision-Language-Action (VLA) architectures and generative world models for L4 autonomous vehicles. Drive scaling, data strategy and global generalization of driving foundation models.

What you will do

• Lead design of end-to-end VLA architectures linking multi-modal perception with linguistic reasoning and action generation
• Drive R&D in generative world models for controllable driving simulation and closed-loop evaluation
• Apply advanced online/offline RL and imitation learning to refine driving policies
• Define scaling laws for driving foundation models, including data curation, automated labeling and post-training at multi-billion parameter scale
• Lead model adaptation for overseas road conditions, traffic laws and driving cultures

Required qualifications

• 5-8 years of expertise in Deep Learning
• Significant track record in VLM, VLA or Embodied AI
• Proven experience training and deploying Foundation Models (Transformers, LLMs) at scale
• Deep understanding of Sequential Decision Making, World Models or Policy Gradient methods
• Mastery of PyTorch and expertise in distributed training (DeepSpeed, Megatron, etc.)
• Product-first mindset: balancing cutting-edge research with deterministic requirements of L4 production vehicles

Benefits

• Competitive compensation package
• Bonus, equity and benefits
• Infrastructure and computational resources for ML development and research
• Snacks, lunches, dinners and fun activities
• Fun, supportive and engaging environment

Before you apply

• Equal opportunity employer

About the company

XPENG is a smart technology company integrating AI and autonomous driving into electric vehicles, eVTOL aircraft and robotics. It focuses on intelligent mobility and cutting-edge R&D in AI and machine learning.