RAG Pipeline Engineer(Freelance | WFH)

About BeGig

BeGig connects AI-first companies with engineers building retrieval-augmented generation systems that work in production.

Your Opportunity

Join BeGig as a RAG Pipeline Engineer and design systems that ground LLM outputs in reliable, up-to-date data.

Role Overview

As a RAG Pipeline Engineer, you will:

• Build document ingestion, chunking, and embedding pipelines.
• Design retrieval strategies using vector databases.
• Integrate RAG pipelines with LLMs and APIs.
• Optimize retrieval accuracy, latency, and cost.
• Implement evaluation and monitoring for RAG quality.

Technical Requirements & Skills

• Experience: 2+ years in AI or backend engineering.
• Tools: LangChain, LlamaIndex, Pinecone, Weaviate, Chroma.
• Languages: Python.
• Concepts: Embeddings, similarity search, context windows.
• Bonus: Experience with production AI systems.

What We’re Looking For

• An engineer who understands why naive RAG fails.
• Strong focus on precision, recall, and performance.
• Comfortable iterating on data quality and retrieval logic.

Why Join Us?

• Impact: Improve trust and accuracy in AI systems.
• Flexibility: AI infrastructure roles across industries.

Network: Work with applied AI and LLM teams.