AI Engineering Expert

该职位来源于猎聘 Job Summary We are seeking an AI Engineer to build and optimize enterprise-grade LLM applications, including RAG systems, AI Agent orchestration, content safety, model evaluation, and backend AI services. You will deliver stable, scalable AI solutions to empower business scenarios. Key Responsibilities

• Evaluate large model performance (accuracy, precision, recall) and build evaluation & trustworthy measurement systems.
• Design and implement domain-specific RAG systems to enhance model accuracy and reliability.
• Build an end-to-end AI Agent Orchestration Platform and develop low-code workflows.
• Develop LLM applications using LangChain/LangGraph for RAG, Agents, and tool usage.
• Optimize prompts, pipelines, and multi-Agent collaboration logic to improve system controllability and performance.
• Develop high-performance backend APIs with FastAPI, ensure service stability, monitoring, and CI/CD deployment.
• Collaborate with cross-functional teams to deliver technical solutions and drive AI capability. Required Qualifications
• Bachelor’s degree or above in Computer Science, AI, or related field.
• 5+ years of Python backend development experience.
• Proficient in FastAPI, RESTful API, asynchronous programming.
• Solid experience with LangChain; familiarity with RAG, Agent, Chain, Memory.
• Experience with LangGraph for workflow orchestration is a strong plus.
• Familiar with mainstream LLM APIs and vector databases (Milvus, Chroma, etc.).
• Knowledge of Git, Docker, Linux, MySQL/PostgreSQL, cloud services.
• Experience in AI Agents, intelligent Q&A, Ragas or enterprise AI systems is a plus.
• Good problem-solving, communication, and teamwork skills.