RL Engineer - Real-Time Planning for Autonomous Driving

XPENG Motors 小鹏汽车; Santa Clara (CA); On-site; USD 179,000 - 304,000; Full time

Benefits offered by this job

Competitive compensation

Snacks, meals and events

Massive data for research

Cutting-edge tech environment

Job summary

XPeng Motors in Santa Clara, CA is seeking a machine learning engineer to design, evaluate and deploy reinforcement learning based planning methods for autonomous driving. You will work with top experts in computer vision, AI systems and software to ensure world-leading performance on our fleet.

The role requires 3–5+ years in RL, strong Python and ML framework skills (PyTorch, TensorFlow), and experience building real-time models.

Qualifications

• Education in Engineering, Robotics, CS with RL/AI focus, or equivalent experience.
• Strong applied RL experience including model design, training, data mining, and analytics.
• 3-5+ years experience with ML frameworks (PyTorch, TensorFlow).
• Strong Python programming with software design skills.
• Solid data structures, algorithms, and large-scale data processing.
• Excellent problem-solving skills.

Responsibilities

• Research and develop RL-based planning methods.
• Design real-time model architectures for vehicle compute platforms.
• Develop offline ML infrastructure for fast adaptation.
• Deliver planning software and collaborate with perception teams.
• Work with large field data to improve autonomous driving technologies.
• Design, run, and analyze experiments to evaluate solutions.
• Partner with system software engineers to ship ML models.
• Collaborate with multi-functional teams.

Skills

Reinforcement Learning

Model Architecture Design

Python

PyTorch

TensorFlow

Realtime Systems

Education

Engineering/CS/Robotics degree

MS/PhD in RL or AI

Tools

ONNX

TensorRT

Job description

XPeng Motors in Santa Clara, CA is seeking a machine learning engineer to design, evaluate and deploy reinforcement learning based planning methods for autonomous driving. You will work with top experts in computer vision, AI systems and software to ensure world-leading performance on our fleet.

The role requires 3–5+ years in RL, strong Python and ML framework skills (PyTorch, TensorFlow), and experience building real-time models.