Multimodal AI Agent Algorithm Engineer

About the team

Our Smart Space AI team is dedicated to creating a world-leading intelligent cockpit agent, with human-machine interaction at its core, aiming to deliver an industry-leading spatial interaction experience. We continuously enhance multimodal perception, multilingual large models’ emotional dialogue capabilities, and core agent abilities such as planning and memory. We are building a multi-agent interaction framework and fostering a robust intelligent agent ecosystem. When needed, intelligent agents can also proactively assist us in thinking and completing tasks, making the interaction between humans and vehicles a truly human-like experience.

Duties and responsibilities

• Responsible for the exploration and implementation of intelligent agent algorithms for the smart cockpit at Li Auto, promoting their application in scenarios such as dialogue systems, decision-making control, and multi-task interaction, while continuously enhancing the user’s intelligent experience.
• Explore the design of agent architectures driven by large models, including but not limited to task planning, memory management, tool invocation, multimodal perception, and reasoning.
• Lead the research, development, and optimization of algorithms that combine large models with intelligent agents, optimizing the integration of large models with reinforcement learning, knowledge graphs, environmental simulators, etc., to enhance the autonomy and generalization ability of intelligent agents.

Requirements

Education/Experience

Master’s degree or above in Computer Science, Artificial Intelligence, Natural Language Processing, Machine Vision, Speech Signal Processing, Mathematics, Physics, or related fields. PhD graduates are preferred (exceptions can be made for candidates with outstanding abilities).

Knowledge/Skills and Competencies

• Technical proficiency in deep learning frameworks such as PyTorch/TensorFlow, as well as strong programming skills in Python/C++/Java/Go. Experience in agent architecture, large model fine-tuning, reinforcement learning, distributed training, etc., is a plus.
• Strong passion for AI technology, with excellent logical thinking, problem breakdown, and communication skills. Publications in conferences such as ACL, EMNLP, NAACL, COLING, AAAI are preferred.

About Li Auto

We're a leading Chinese new energy vehicle company that designs, develops, manufactures, and sells premium smart electric vehicles (EVs). Through product, technology, and business model innovations, we provide families with safer, more comfortable, and more convenient products and services.