Key Responsibilities
- Design, develop and maintain AI Agent applications powered by Large Language Models (LLMs), including intelligent Q&A, task planning, tool calling, workflow orchestration, multi-agent collaboration and long-term memory.
- Design technical solutions and build production-ready AI applications using leading LLMs and Agent frameworks, covering solution architecture, prototyping, implementation, testing, deployment and continuous optimisation.
- Develop and optimise key AI capabilities including: Prompt Engineering, Retrieval-Augmented Generation (RAG), Enterprise Knowledge Base, Function Calling, Model Context Protocol (MCP) integrations
- Integrate LLM capabilities with existing enterprise applications, business systems, databases and third-party APIs to automate and enhance business workflows.
- Establish evaluation and monitoring mechanisms for AI applications, continuously improving: task completion rate, response accuracy, system reliability, latency, model inference cost
- Participate in AI product planning, system architecture design, API design, technical reviews and end-to-end project delivery.
- Keep up to date with the latest developments in LLMs, AI Agents and related technologies, conducting technical research, proof-of-concepts and production implementation.
- Collaborate closely with Product Managers, AI Scientists, Backend Engineers and business stakeholders to independently deliver core product features.
Requirements
Education
- Bachelor's degree or above in Computer Science, Artificial Intelligence, Software Engineering, Data Science or a related discipline.
Experience
- Minimum 5 years of software engineering or backend development experience with strong software engineering fundamentals and coding best practices.
- Strong proficiency in Python.
- Solid understanding of: data structures, oriented design, design patterns, concurrent programming, RESTful API development, exception handling
- Experience developing backend services using FastAPI, Flask, Django or other modern Python frameworks.
AI / LLM Experience
- Hands-on experience building LLM-powered applications using one or more of the following:
OpenAI, Claude, Gemini, Qwen, DeepSeek, or equivalent commercial/open-source models.
AI Agents, Prompt Engineering, Retrieval-Augmented Generation (RAG), Function Calling, Model Context Protocol (MCP), Workflow orchestration
- Experience with one or more AI frameworks/platforms, such as:
LangChain, LangGraph, LlamaIndex, AutoGen, Dify, FastGPT, Coze
Engineering Skills
- Experience with Git, Docker, Linux and CI/CD pipelines.
- Familiarity with production deployment, monitoring and troubleshooting.
- Experience working with relational, vector or search databases, including one or more of:
PostgreSQL, MySQL, Redis, Milvus, Elasticsearch, FAISS
Preferred Qualifications
Candidates with one or more of the following will be highly regarded:
- Production experience building AI Agents, enterprise knowledge bases, intelligent assistants or multi-agent systems.
- Experience in LLM fine-tuning, embedding models, reranking, model evaluation, inference optimisation or model serving.
- Experience with microservices, distributed systems, cloud-native architecture and high-concurrency backend systems.
- Industry experience in Energy Storage (BESS), Power & Energy, Industrial IoT, Smart Energy or Enterprise Digitalisation.
Soft Skills
- Strong analytical thinking and problem-solving skills.
- Ability to independently own and deliver end-to-end technical modules.
- Excellent communication and cross-functional collaboration skills.
- Ability to read and understand English technical documentation.
