AI Engineer (Managed Services)
Core
Architect, build, and deploy production-grade LLM applications including RAG systems, intelligent knowledge bases, and autonomous multi-agent workflows.
Role type
Senior IC AI Engineer (LLMs & Agentic AI)
Builds
Enterprise LLM-powered applications, RAG systems, and multi-agent orchestration pipelines.
Domain
Artificial Intelligence / Large Language Models / Enterprise Software
Deliverable
production ML models
Required skills
LLM application development, RAG system architecture, prompt engineering, multi-agent orchestration, model deployment & optimization, model fine-tuning, LLM evaluation, Python programming
Preferred skills
Agent frameworks (LangGraph, AutoGen), MCP integrations, prompt optimization tools, model distillation, cloud GPU cost optimization
Technologies
DeepSeek, Qwen, Kimi, Llama 3.x, Mistral, LangChain, LlamaIndex, Haystack, Milvus, ChromaDB, Qdrant, Weaviate, Pinecone, vLLM, TensorRT-LLM, TGI, Ollama, Xinference, SGLang, Kubernetes, PyTorch, FastAPI
Responsibilities
Design and develop enterprise LLM-powered applications; Architect and implement end-to-end RAG systems; Develop and optimize Prompt Engineering strategies; Design and build AI Agent systems using ReAct and multi-agent collaboration patterns; Deploy and optimize open-source Chinese LLMs for on-premise environments; Implement efficient fine-tuning pipelines; Build and maintain LLM evaluation frameworks; Implement production monitoring for LLM systems
Seniority
Senior, hands-on IC