Senior Staff Research Engineer – Reinforcement Learning for AI Agents

XPENG is a leading smart technology company at the forefront of innovation, integrating advanced AI and autonomous driving technologies into its vehicles, including electric vehicles (EVs), electric vertical take-off and landing (eVTOL) aircraft, and robotics. With a strong focus on intelligent mobility, XPENG is dedicated to reshaping the future of transportation through cutting-edge R&D in AI, machine learning, and smart connectivity.

We are looking for exceptional Research Engineers / Scientists to design learning systems that allow agents to plan over long horizons, learn effective strategies, and improve through experience.

This role sits at the intersection of reinforcement learning , large language models, and real-world autonomous systems . Autonomous systems must operate reliably in complex, dynamic environments. We believe the next generation of autonomy will involve learning agents that continuously improve through interaction, feedback, and large-scale data . You will help build the learning systems that power these agents .

Key Responsibilities:

• Reinforcement learning methods for LLM-driven agents and decision systems.

• Policy optimization for long-horizon reasoning and planning.

• Learning from human or AI feedback (RLHF / RLAIF).

• Agent training pipelines built on top of our agent infrastructure platform.

• Evaluation and benchmarking systems for agent capabilities.

• Learning loops that integrate real-world and simulation data.

• Contribute to AI systems that continuously improve after deployment .

Basic Qualifications

• MS or PhD in Computer Science, AI, Machine Learning, Robotics, or a related field.

• Strong background in reinforcement learning or machine learning.

• Experience implementing RL algorithms such as PPO, Actor-Critic, or policy gradient methods.

• Strong programming skills in Python with PyTorch or JAX.

• Experience building ML training systems or infrastructure.

Preferred Qualifications

• Experience with RLHF or preference learning.

• Experience with LLM agents or tool-using AI systems.

• Multi-agent systems or long-horizon planning.

• Simulation environments for RL.&l