企业微信-AI应用后台开发工程师-AI大模型应用（成都/北京）
Core
Design, develop, and iterate the backend system for WeCom AI applications, integrating large model capabilities to serve intelligent dialogue, RAG, and task automation scenarios.
Role type
Senior backend engineer (LLM application & RAG)
Builds
High-availability, low-latency model invocation and service scheduling frameworks; distributed backend services for AI features.
Domain
Enterprise software / Large Language Models / Retrieval-Augmented Generation
Deliverable
production ML models
Required skills
C++, Linux/Unix backend development, distributed systems, RAG implementation, LLM integration, performance tuning, high-concurrency system design
Preferred skills
ToB project experience, independent exploration of frontier technologies
Technologies
C++, Linux, Unix, RAG, LLM
Responsibilities
Design and develop WeCom AI application backend systems; build model calling and service scheduling frameworks; optimize RAG retrieval and generation performance; collaborate with AI product and algorithm teams; ensure reliability of distributed services under high concurrency.
