About this role
**Job Description** The AI Full-Stack Engineer will work closely with Product, Forward Deployed Engineering (FDE), and business teams to rapidly deliver production-ready AI capabilities and MVP tools for real-world business scenarios. Key responsibilities include: - Design, develop, and maintain AI Agent application modules, including conversational interfaces, knowledge bases, workflow engines, Agent configuration, and Skill management. - Integrate large language model capabilities, including multi-turn conversation, Retrieval-Augmented Generation (RAG), tool/function calling, prompt management, workflow orchestration, and Skill integration. - Build and integrate Agent Skills and tools, such as API Skills, workflow-based Skills, script-based Skills, MCP tools, and connections to internal enterprise systems. - Contribute to the design of Skill execution mechanisms, access control, context management, tool protocols, and end-to-end invocation flows. - Develop frontend experiences including Chat UI, Agent configuration pages, Skill management interfaces, workflow visualization, and operational dashboards. - Develop backend APIs, data models, job scheduling, and system integration services to support a reliable and scalable Agent platform. - Help establish a context data feedback loop by capturing AI interactions, user selections, edits, feedback, and outcome data in structured formats. - Partner with Product, FDE, and business stakeholders to translate evolving requirements into practical solutions and iterate quickly. - Participate in testing, staged releases, issue investigation, log analysis, and continuous improvement to enhance system reliability and user experience. **Qualifications** - 2–5 years of relevant software development experience, with experience delivering complete web applications, internal tools, or enterprise systems. - Bachelor’s degree or above in Computer Science, Software Engineering, Information Systems, or a related field preferred. - Proficiency in at least one programming language: Python, TypeScript, or JavaScript. - Experience with Vue or React, including frontend pages, reusable components, and state management. - Familiarity with FastAPI or comparable backend frameworks, with the ability to independently develop APIs, service logic, and basic integrations. - Familiarity with PostgreSQL, MySQL, Redis, and related database or caching systems. - Understanding of core LLM application concepts, including prompting, RAG, embeddings, tool/function calling, and Agent workflows. - Strong engineering discipline, code quality standards, and collaborative working practices. - Ability to work effectively amid ambiguous requirements, break down problems, and iterate quickly with product and business stakeholders. - Strong Chinese communication skills and the ability to read English technical documentation. **Preferred Qualifications** - Experience with LLM, Agent, RAG, or workflow automation projects. - Experience with frameworks or tools such as LangChain, LlamaIndex, Dify, n8n, AutoGen, CrewAI, or MCP. - Frequent use of AI-assisted development tools such as Cursor, Claude Code, or GitHub Copilot. - Experience building Chat UIs, knowledge-base systems, workflow engines, low-code platforms, or enterprise internal tools. - Experience with authorization systems, audit logging, analytics instrumentation, observability dashboards, or administrative platforms. - Experience in architecture, real estate, engineering, design, or the AEC industry. **Working Style** We value engineers who can turn AI prototypes into reliable, usable business features; learn quickly through experimentation; stay close to real user workflows and feedback; take ownership; and proactively drive problems through to resolution.
At Surbana Jurong, we put talent, hard work, teamwork and a fun workplace together to approach problems and solve them creatively and collaboratively. Join us in making a positive impact on the world!