Department: AI Agent Research Center 

| Location: Hong Kong / Shenzhen

Experience: Graduate / Early Career 

| Openings: 10

About the Role:

You will help build learning-capable AI agents that interact with real-world business environments, learn decision policies for pricing/inventory, and optimize behavior through feedback. This is about RL + LLM + Multi-agent coordination in real industrial systems.

Key Focus:

• Design agent-environment interaction systems (observations, actions, rewards).

• Apply RL to pricing optimization, inventory allocation, and fulfillment scheduling.

• Build long-horizon planning and multi-step reasoning pipelines.

• Implement preference learning and feedback optimization (RLHF / RLAIF).

• Construct simulation environments and offline evaluation pipelines from real business data.

Ideal Experience:

• Background in RL, agents, or decision systems; Strong Python & PyTorch.

• Ability to abstract real-world problems into states, actions, and rewards.

• Nice to have: Multi-agent experience, Game theory, or Supply chain optimization.

• Tech Stack: Python, PyTorch, Distributed RL, Agent frameworks.