About this role
We are Lenovo. We do what we say. We own what we do. We WOW our customers.
Lenovo is a US$83 billion revenue global technology powerhouse, ranked #153 in the Fortune Global 500, and serving millions of customers every day in 180 markets. Focused on a bold vision to deliver Smarter Technology for All, Lenovo has built on its success as the world’s largest PC company with a full-stack portfolio of AI-enabled, AI-ready, and AI-optimized devices (PCs, workstations, smartphones, tablets), infrastructure (server, storage, edge, high performance computing and software defined infrastructure), software, solutions, and services. Lenovo’s continued investment in world-changing innovation is building a more equitable, trustworthy, and smarter future for everyone, everywhere. Lenovo is listed on the Hong Kong stock exchange under Lenovo Group Limited (HKSE: 992) (ADR: LNVGY).
This transformation together with Lenovo’s world-changing innovation is building a more inclusive, trustworthy, and smarter future for everyone, everywhere. To find out more visit www.lenovo.com (https://www.lenovo.com), and read about the latest news via our StoryHub (https://news.lenovo.com/).
Job Responsibilities:
1. Application development of AI Agent
- Responsible for building enterprise-level intelligent agent applications, such as intelligent data analysis assistants, intelligent reporting systems, knowledge question answering, process automation, and other scenarios.
- Master the construction of RAG (Retrieval Augmented Generation) systems, including prompt engineering, vector databases, embeddings, and retrieval optimization strategies (hybrid retrieval, reranking, query reformulation, etc.).
- Implement task planning, dialogue management, intent recognition, tool invocation, process engineering, RAG, etc. for intelligent agents based on LangChain, LangGraph, LlamaIndex, and Agent Framework.
- Able to independently complete the entire process of an intelligent agent, from design to launch.
- Promote continuous optimization of AI Agent in terms of architecture and performance.
- Implement A2A (Agent-to-Agent) orchestration, multi-agent collaborative task design, and implementation for intelligent agents.
2. Building Intelligent BI Capabilities
- Automatically convert natural language into data queries (SQL/DSL), and interface with enterprise data APIs and data warehouses.
- Build capabilities such as logical analysis, field mapping, indicator definition, exception handling, and result interpretation for intelligent BI.
- Collaborate with the data team to optimize data calibers, indicator systems, and knowledge graphs.
- Utilize vector retrieval (Milvus/PGVector) + structured data query to build a hybrid RAG
- Optimize recall, enhance data context, reduce hallucinations, and improve answer accuracy.
Job Requirements
- Major in computer science or related fields is preferred, with a bachelor's degree or above.
- Proficient in using AI programming tools (such as Cursor, Copilot, GPT, Qoder, etc.), which can significantly enhance development efficiency.
- Proficient in the Python programming language, with experience in designing complex backend system architectures, proficiency in frameworks such as FastAPI, strong software framework and application design capabilities, high-performance architecture design, and a deep understanding of design patterns.
- Possess excellent abilities in code writing, debugging, optimization, and engineering thinking; be familiar with the Linux development environment, version control Git, and Docker operations.
- Experience in developing RAG applications, question-answering systems, SQL automatic generation, or data analysis assistants.
- Familiar with the design patterns of AI Agents: ReAct, Plan-and-Execute, Reflection, etc.
- Proficient in the use of vector databases (such as Milvus, Chroma) and traditional databases (PostgreSQL, Sql Server, Mysql, Redis, Elasticsearch);
- Familiar with any of the AI agent frameworks: LangChain/LangGraph, LlamaIndex, CrewAI, AutoGen, or Agent Framework.
- Proficient in basic front-end development (Vue/React, either) for developing user interfaces or result display pages for intelligent agents.