Responsibilities: 1. Assist in building AI-powered interactive demo systems for entertainment scenarios, where user inputs (e.g., photos) are analyzed to generate real-time feedback and suggestions. 2. Develop and integrate AI models (e.g., vision or multimodal models) into edge-cloud pipelines, including data upload, cloud inference, and response delivery. 3. Implement backend services and APIs to support AI agent workflows, including handling user inputs, model invocation, and result generation. Requirements： Basic experience with AI/ML (e.g., coursework, projects, or internships), especially in computer vision or multimodal models. Programming skills in Python; familiarity with backend development (e.g., FastAPI, Flask, Node.js) is a plus. Understanding of how to use and deploy AI models (e.g., calling APIs, running inference, or simple model integration).