AI搜索架构工程师
Core
Design and build large-scale AI search architecture and RAG engines for Douyin and Toutiao, serving hundreds of millions of users with end-to-end modeling and distributed system optimization.
Role type
Senior IC AI Search Architect (LLM & RAG)
Builds
Large-scale AI search RAG engines, LLM-based search systems, and high-throughput distributed machine learning infrastructure.
Domain
Internet / AI Search / Large Language Models / Distributed Systems
Deliverable
production ML models
Required skills
Computer science fundamentals, data structures and algorithms, distributed system theory, machine learning principles, C++ development, GPU inference optimization, RAG framework experience, recommendation/search/ad engine experience.
Preferred skills
Linux performance tuning, distributed database/compute framework development, large-scale sparse model implementation, multi-modal understanding, user behavior modeling.
Responsibilities
Build a complete RAG-functional LLM search engine for Douyin AI Search; Optimize LLM search components including web retrieval and large model inference; Design offline personalized AI search capabilities for accurate Q&A; Architect flexible and scalable systems to support rapid business growth.
Seniority
Senior, hands-on IC
