Software Engineer
Core
Design and develop enterprise-grade AI applications, implementing LLM technology into real-world business scenarios including intelligent Q&A and document generation.
Role type
Senior AI Application Engineer (LLM/RAG)
Builds
RAG systems, AI Agents, model service middleware, and enterprise knowledge bases with vectorized retrieval.
Domain
Enterprise AI / Large Language Models / RAG
Deliverable
production ML models | product features
Required skills
Python, LangChain, LlamaIndex, RAG architecture, Prompt Engineering, Model Fine-tuning (LoRA/SFT), Docker, Kubernetes, RESTful API design, Vector Databases (Milvus/Pinecone/Chroma/Qdrant), Relational Databases (PostgreSQL/MySQL), Redis.
Preferred skills
AI Agent development, Enterprise document parsing (PDF/Word/Excel), LLMOps monitoring.
Technologies
LangChain, LlamaIndex, FastAPI, Flask, Docker, Kubernetes, Milvus, Pinecone, Chroma, Qdrant, PostgreSQL, MySQL, Redis, GPT, Claude, DeepSeek, Tongyi Qianwen.
Responsibilities
Develop RAG systems and AI Agents using LangChain/LlamaIndex; Design prompt engineering and optimize model outputs; Containerize and deploy AI services; Integrate AI applications with existing enterprise systems (ERP/CRM/OA); Mentor junior developers and communicate with product/business teams.
Seniority
Mid-Senior, hands-on IC