技能档案

RAG

此技能定义了各角色和级别的期望。

Machine Learning & AI LLM & Generative AI

角色数

包含此技能的角色

级别数

结构化成长路径

必要要求

其余 5 个可选

Machine Learning & AI

LLM & Generative AI

2026/2/22

选择当前级别并对比期望。下方卡片显示晋升所需掌握的内容。

各级别期望

表格展示从初级到首席的技能深度变化。点击行查看详情。

角色	必要性	描述
LLM Engineer		Knows RAG basics: retrieval + generation, basic pipeline with embedding and vector search. Builds simple RAG pipeline on LangChain with ChromaDB for QA task under mentor guidance.

角色	必要性	描述
LLM Engineer		Independently designs production RAG: advanced chunking, hybrid retrieval, re-ranking. Configures metadata filtering, conversation history, and source attribution. Evaluates quality via RAGAS.

角色	必要性	描述
LLM Engineer		Designs enterprise RAG systems: multi-source retrieval, agentic RAG, query routing. Optimizes retrieval quality through fine-tuning retrievers, custom re-rankers, and adaptive chunking strategies.

角色	必要性	描述
LLM Engineer		Defines RAG strategy for the LLM team. Establishes best practices for RAG architecture, data ingestion, quality monitoring. Coordinates RAG system as platform for multiple products.

角色	必要性	描述
LLM Engineer		Shapes enterprise RAG platform for the organization. Defines approaches to unified knowledge bases, multi-tenant RAG, and governance. Ensures scalability and quality at the scale of millions of documents.

Junior 1 要求

LLM Engineer

Knows RAG basics: retrieval + generation, basic pipeline with embedding and vector search. Builds simple RAG pipeline on LangChain with ChromaDB for QA task under mentor guidance.

Middle 1 要求

LLM Engineer

Independently designs production RAG: advanced chunking, hybrid retrieval, re-ranking. Configures metadata filtering, conversation history, and source attribution. Evaluates quality via RAGAS.

Senior 1 要求

LLM Engineer

Designs enterprise RAG systems: multi-source retrieval, agentic RAG, query routing. Optimizes retrieval quality through fine-tuning retrievers, custom re-rankers, and adaptive chunking strategies.

Lead / Staff 1 要求

LLM Engineer

Defines RAG strategy for the LLM team. Establishes best practices for RAG architecture, data ingestion, quality monitoring. Coordinates RAG system as platform for multiple products.

Principal 1 要求

LLM Engineer

Shapes enterprise RAG platform for the organization. Defines approaches to unified knowledge bases, multi-tenant RAG, and governance. Ensures scalability and quality at the scale of millions of documents.

👁 关注 ✏️ 建议修改

正在加载评论...