AI RAG Solutions Architect (Contract)

Location: Remote-first (Work from anywhere)
Type: 3–6 month contract | ~10–20 hours/week (Days and times to be discussed) | Start: August 2025

Your Mission

We're looking for an AI architect who knows how to make LLMs useful in the real world. You’ll own the architecture behind smart, scalable Retrieval-Augmented Generation (RAG) systems — from design to delivery. These solutions will sit at the heart of cutting-edge digital platforms, where search, personalisation, and performance matter.

What You'll Do

• Architect and deliver RAG pipelines using tools like LangChain and Pinecone/Weaviate
• Solve real-world problems: improve search, scale personalisation, reduce latency
• Work across teams — tech, data, marketing — to shape how AI shows up in the product
• Build with performance, compliance (GDPR, POPIA), and handover in mind
• Document the right way: architecture, ops flows, and integration touchpoints
• Share your know-how via workshops and tooling guidance for internal teams

What You Bring

• You’ve designed and shipped RAG systems that actually got used
• You know your way around LLMs, semantic search, LangChain, and vector DBs
• You’re fluent in Python and know how to plug AI into real product environments
• You’ve deployed on AWS/GCP/Azure and care about cost, security, and uptime
• You think like a builder, not just an advisor — and your docs prove it

Bonus: you’ve worked with CMSs (Payload or similar), or in luxury, travel, or content-led tech

Job Schedule

All times are shown in America/Los_Angeles time.