Context / Retrieval Engineer (RAG Specialist)

DeWinter Group; Campbell (CA); Remote; USD 69,000 - 241,000; Part time

Job summary

DeWinter Group is seeking a Context/Retrieval Engineer to join a 12-month contract focused on optimizing Retrieval-Augmented Generation (RAG) pipelines and hybrid search systems. You will work remotely with a client leader in AI testing and Generative AI solutions.

The ideal candidate has 3+ years in Information Retrieval or AI Engineering, deep expertise with vector databases (Pinecone, Chroma, Milvus) and LangChain/LlamaIndex, and strong Python/SQL/NLP skills, with autonomous work style and

Qualifications

• 3+ years in Information Retrieval or AI Engineering.
• Subject-matter expert in vector databases and LangChain/LlamaIndex.
• Able to work autonomously and manage time to meet goals.
• Proficient in Python, SQL, and NLP techniques.
• Strong communication with project team.

Responsibilities

• Optimize RAG pipelines to improve AI response accuracy and relevance.
• Implement chunking strategies and metadata tagging for documents.
• Select and fine-tune embedding models for domain semantics.
• Design hybrid search using vector similarity and BM25.
• Benchmark vector databases for speed and memory efficiency.

Skills

AI Engineering

Vector Databases

LangChain

Python

SQL

NLP

Autonomy

Communication

Tools

Pinecone

Chroma

Milvus

LangChain

LlamaIndex

Job description

About The Opportunity

Our client, a leader in AI testing and Generative AI solutions, is looking for a skilled

Key Responsibilities & Deliverables

This role is focused on the successful completion of specific tasks and deliverables. Your responsibilities will include:

• Optimizing Retrieval-Augmented Generation (RAG) pipelines to improve the accuracy and relevance of AI responses.
• Implementing advanced "chunking" strategies and metadata tagging for enterprise documents.
• Selecting and fine-tuning embedding models to better capture domain-specific semantic meaning.
• Designing hybrid search systems combining vector similarity with traditional keyword search (BM25).
• Benchmarking various vector databases to ensure high retrieval speed and low memory overhead.

Title: Context/Retrieval Engineer

Job Type: Contract

Contract Length: 12 Months

Pay Range: $50/hr – $175/hr

Start Date: ASAP

Location: Remote

About The Opportunity

Our client, a leader in AI testing and Generative AI solutions, is looking for a skilled Context/Retrieval Engineer (RAG Specialist) to join their team for a 12-month engagement. This project involves optimizing Retrieval-Augmented Generation (RAG) pipelines to improve the accuracy and relevance of AI responses. This is a high-impact role that requires a self-motivated professional who can hit the ground running and deliver results quickly.

Key Responsibilities & Deliverables

This role is focused on the successful completion of specific tasks and deliverables. Your responsibilities will include:

• Optimizing Retrieval-Augmented Generation (RAG) pipelines to improve the accuracy and relevance of AI responses.
• Implementing advanced "chunking" strategies and metadata tagging for enterprise documents.
• Selecting and fine-tuning embedding models to better capture domain-specific semantic meaning.
• Designing hybrid search systems combining vector similarity with traditional keyword search (BM25).
• Benchmarking various vector databases to ensure high retrieval speed and low memory overhead.

Required Skills & Experience

We are looking for someone with a proven track record of successful contract engagements. The ideal candidate will have:

• 3+ years of experience in Information Retrieval or AI Engineering.
• Deep expertise in Vector Databases (Pinecone, Chroma, Milvus) and LangChain/LlamaIndex. This isn't a learning role—you need to be a subject matter expert.
• Demonstrated ability to work autonomously and manage your own time effectively to meet project goals.
• Experience with Python, SQL, and natural language processing (NLP) techniques.
• Strong communication skills to provide clear and concise status updates to the project team.