Remote positions

Remote LlamaIndex Jobs

Browse vetted remote LlamaIndex positions — RAG pipeline engineering, document intelligence, and LLM retrieval system development at AI-first companies.

Vetted companies
Remote worldwide
All job types
RAG Engineer LLM Retrieval Engineer Document AI Developer LlamaIndex Developer Knowledge Base Engineer

Top matching AI roles

Filters

AI Specialization

Job Type

Experience Level

Get matched to AI roles

Create your free profile and let companies find you.

Join as talent — free

Jobs & Projects

Neo4J
lead
Full-time
English
Open job
Neo4J

Posted 1 day ago

Consulting Engineer

Full-time
English
Open job
Llamaindex

Posted 2 days ago

Head of Engineering

executive
Full-time
English
llamaindex llm fine-tuning
Open job
S
staff
Full-time
English
$230K – $360K / year
machine learning python pytorch pandas generative ai +13 more
Open job
ClickHouse
Full-time
English
python langchain llm llamaindex typescript +2 more
Open job
Fireworks AI
staff
Full-time
English
Open job
Snowflake
senior
Full-time
English
machine learning python aws pytorch pandas +13 more
Open job
Snowflake
principal
Full-time
English
Open job
ClickHouse
senior
Full-time
English
Open job
ClickHouse
senior
Full-time
English
Open job

Role guide

What to expect in remote LlamaIndex jobs

LlamaIndex is the go-to framework for building RAG systems and document intelligence applications. Remote LlamaIndex jobs involve designing retrieval pipelines, connecting LLMs to private knowledge bases, and building production systems that answer questions accurately over large document corpora. These roles require deep understanding of chunking strategies, embedding models, and retrieval evaluation.

What you'll work on

  • Build RAG systems that answer questions over enterprise knowledge bases and documents
  • Design multi-document retrieval pipelines with re-ranking for accuracy
  • Create agents that query structured and unstructured data sources with LlamaIndex
  • Develop evaluation pipelines to measure retrieval and generation quality

What companies look for

  • LlamaIndex core abstractions — nodes, indices, query engines, retrievers
  • Chunking strategy design and embedding model selection for retrieval quality
  • Integration with vector stores (Pinecone, Weaviate, pgvector) and LLM APIs

Frequently asked questions

What is the difference between LlamaIndex and LangChain for remote jobs?

LlamaIndex specialises in document retrieval and RAG pipelines. LangChain is broader — covering agents, chains, and general LLM orchestration. Many companies use both. Job listings often list both as desirable.

Do LlamaIndex jobs require vector database experience?

Almost always. Pinecone, Weaviate, Chroma, and pgvector are the most common. Understanding how embedding similarity search works is essential for RAG engineering roles.

Browse other remote AI jobs

Are you a LlamaIndex specialist? Get hired remotely.

Create my profile — it's free