技能档案

Embeddings & Vector DB

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 text embeddings and vector database basics. Generates embeddings via sentence-transformers, stores and searches in ChromaDB. Understands cosine similarity and basic semantic search.

角色	必要性	描述
LLM Engineer		Independently designs embedding pipelines: model selection (OpenAI, Cohere, BGE), chunking strategies, and metadata filtering. Configures Pinecone/Weaviate for production workloads with recall optimization.

角色	必要性	描述
LLM Engineer		Designs scalable embedding infrastructure: hybrid search (dense + sparse), re-ranking, multi-vector retrieval. Optimizes latency and recall through fine-tuning embedding models and index tuning.

角色	必要性	描述
LLM Engineer		Defines embedding and vector DB strategy for the LLM platform. Establishes guidelines for embedding model selection, vector DB, index sharding, and retrieval quality monitoring.

角色	必要性	描述
LLM Engineer		Shapes enterprise embedding infrastructure strategy. Defines approaches to centralized embedding services, managing billions of vectors, cost optimization, and retrieval quality at scale.

Junior 1 要求

LLM Engineer

Knows text embeddings and vector database basics. Generates embeddings via sentence-transformers, stores and searches in ChromaDB. Understands cosine similarity and basic semantic search.

Middle 1 要求

LLM Engineer

Independently designs embedding pipelines: model selection (OpenAI, Cohere, BGE), chunking strategies, and metadata filtering. Configures Pinecone/Weaviate for production workloads with recall optimization.

Senior 1 要求

LLM Engineer

Designs scalable embedding infrastructure: hybrid search (dense + sparse), re-ranking, multi-vector retrieval. Optimizes latency and recall through fine-tuning embedding models and index tuning.

Lead / Staff 1 要求

LLM Engineer

Defines embedding and vector DB strategy for the LLM platform. Establishes guidelines for embedding model selection, vector DB, index sharding, and retrieval quality monitoring.

Principal 1 要求

LLM Engineer

Shapes enterprise embedding infrastructure strategy. Defines approaches to centralized embedding services, managing billions of vectors, cost optimization, and retrieval quality at scale.

👁 关注 ✏️ 建议修改

正在加载评论...