AI Fullstack Engineer

Key Responsibilities

• Develop frontend architecture for AI Agent based on mainstream frameworks, build modules including AI chat, knowledge base search, data visualization, workflow orchestration and auto AI report preview.
• Integrate LLM, retrieval and customized AI Skill APIs, implement streaming response, long-content rendering and professional interaction logic for AI scenarios.
• Build lightweight backend services with Node.js, develop APIs and conduct database access to complete full-link joint debugging independently.
• Develop visualization dashboards for semiconductor parameters, process curves and benchmark data; support filtering, batch export and drag operations.
• Standardize frontend components, optimize loading performance, large-data rendering and code maintainability.
• Cooperate with global cross-functional teams to iterate features, fix online issues and match industrial workflow requirements.
• Manage frontend deployment, CI/CD and monitoring to guarantee stable online operation.

Basic Requirements

• Bachelor's degree in Computer Science, Software Engineering, or related fields, with 3+ years of full-stack development experience and strong frontend engineering capability.
• Proficient in React or Vue, TypeScript, state management, responsive design, and modern frontend development practices.
• Experience building complex data visualizations using libraries such as ECharts, AntV, D3.js, or similar frameworks.
• Proficient in Python and experienced with backend development using FastAPI (or similar frameworks) for building RESTful APIs and AI application services.
• Experience with Node.js and/or Java (Spring Boot) for backend service development is a plus, with the ability to design, develop, and debug RESTful APIs.
• Experience with relational databases (e.g., MySQL or PostgreSQL), API integration, and backend service architecture.
• Familiar with real-time communication technologies such as Server-Sent Events (SSE), WebSocket, or streaming APIs, especially for AI chat, agent workflows, and long-running inference tasks.or streaming APIs, especially for AI chat and long-running task scenarios.
• Proficient with Git, frontend build tools, deployment workflows, and CI/CD practices.
• Strong problem-solving skills and the ability to translate business requirements into scalable technical solutions.
• Good communication skills for cross-regional collaboration and the ability to read English technical documentation and fluent in English.

Preferred Qualifications

Experience building B2B SaaS products, scientific research platforms, or systems related to semiconductors, materials, manufacturing, or industrial domains.
Hands-on experience developing AI applications, AI Agents, workflow builders, prompt management systems, or AI Skill/Tool integration platforms.
Familiarity with LLM ecosystems, including model APIs, Retrieval-Augmented Generation (RAG), vector databases, semantic search, and AI application architectures.
Exposure to AI algorithm development, model evaluation, prompt engineering, or data processing pipelines is a plus, but not required.
Understanding of streaming AI interactions, multi-step agent workflows, and user experience design for AI products.
Experience working in global and distributed engineering teams.

What We Offer

Work on high-growth vertical AI track combining semiconductor and large model technology, build differentiated technical competitiveness.
Role prioritizes frontend strengths with only basic backend needed; grow into an AI application frontend specialist or full-stack expert.
Central position in product development with high autonomy in interaction and component design.
Competitive compensation aligned with international tech standards, global teamwork opportunities and clear long-term career development paths.
All AI interaction and visualization assets can be accumulated as portfolio for future career advancement.