Senior RL Engineer - Humanoid Robotics (Equity)

XPENG; Santa Clara (CA); On-site; USD 175,000 - 296,000; Full time

Benefits offered by this job

Snacks, meals, and team activities

Job summary

XPENG is seeking a research engineer to advance deep-learning methods for legged locomotion and whole-body control in humanoid robots. You will develop end-to-end motion controllers using reinforcement learning or imitation learning, and design experiments to evaluate RL controllers, addressing sim-to-real challenges.

The role requires an advanced degree and 1–3+ years in DL, Python, and PyTorch, with knowledge of PPO, DQN, SAC. C++ is a plus and robotics hardware experience is valued.

Qualifications

• Advanced degree in Mechanical Engineering, Computer Science, Robotics, or a related field.
• Open to fresh graduates.
• Proficiency in Python and strong software design skills.
• 1–3+ years of experience with deep learning frameworks like PyTorch.
• Strong understanding of reinforcement learning and imitation learning techniques.
• Proven experience applying algorithms such as PPO, DQN, SAC to real-world problems.

Responsibilities

• Research, implement, and evaluate deep-learning-based methods for legged locomotion and whole-body control problems in humanoid robots.
• Develop and refine end-to-end robot motion controllers using reinforcement learning, imitation learning, or other advanced techniques.
• Design, execute, and analyze experiments to evaluate RL controllers and address sim-to-real challenges.
• Stay updated and integrate the latest advancements in academic and engineering research for humanoid robotics.

Skills

Python

Deep learning

Reinforcement learning

Imitation learning

PyTorch

RL algorithms

Education

Advanced degree (Mechanical Engineering, Computer Science, Robotics, or related)

Tools

C++

Job description

XPENG is seeking a research engineer to advance deep-learning methods for legged locomotion and whole-body control in humanoid robots. You will develop end-to-end motion controllers using reinforcement learning or imitation learning, and design experiments to evaluate RL controllers, addressing sim-to-real challenges.

The role requires an advanced degree and 1–3+ years in DL, Python, and PyTorch, with knowledge of PPO, DQN, SAC. C++ is a plus and robotics hardware experience is valued.