Perfil de habilidad

Embeddings & Vector DB

Esta habilidad define expectativas en roles y niveles.

Machine Learning & AI LLM & Generative AI

Roles

donde aparece esta habilidad

Niveles

ruta de crecimiento estructurada

Requisitos obligatorios

los otros 5 opcionales

Machine Learning & AI

LLM & Generative AI

22/2/2026

Selecciona tu nivel actual y compara las expectativas.

Qué se espera en cada nivel

La tabla muestra cómo crece la profundidad desde Junior hasta Principal.

Rol	Obligatorio	Descripción
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.

Rol	Obligatorio	Descripción
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.

Rol	Obligatorio	Descripción
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.

Rol	Obligatorio	Descripción
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.

Rol	Obligatorio	Descripción
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 requisitos

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 requisitos

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 requisitos

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 requisitos

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 requisitos

LLM Engineer

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

Cargando comentarios...