We are building a knowledge assistant for our internal teams and need a developer to design and implement the RAG (Retrieval-Augmented Generation) pipeline — from document ingestion to vector search to response generation.
Responsibilities
Design and build the end-to-end RAG pipeline
Implement document chunking, embedding, and indexing strategies
Integrate with OpenAI or Anthropic for generation
Build an evaluation framework for retrieval and answer quality
Document the system for internal engineering team
Requirements
Experience building RAG systems with LlamaIndex or LangChain
Familiarity with vector databases (Pinecone, Chroma, Qdrant, Weaviate)
Strong Python and understanding of embedding models
Able to evaluate retrieval quality and improve relevance
Comfort working with unstructured data (PDFs, Word docs, Confluence)
Benefits
Greenfield RAG project — your design decisions
Remote
Equity
Learning budget
Small, smart team
Job Type
Full-time
Level
Mid-level
Language
English
Salary Range
$100,000 – $130,000
AI Expertise
NLP & Prompt Engineering
data science & analytics
data science