Data Solutions Architect

PBT Group; Cape Town; On-site; ZAR 500 000 - 600 000; Full time

Job summary

A tech-focused company in Cape Town seeks a Data Solutions Architect/Senior Data Engineer to join their Data and AI team. This role involves designing scalable data pipelines and architectures on Azure, ensuring compliance and performance in data management. Candidates should have over 7 years of relevant experience, strong Azure skills, and be adept in SQL and Python. This opportunity allows you to build cutting-edge cloud solutions from the ground up, contributing to an innovative data platform.

Qualifications

• 7+ years’ experience as a Data Engineer or Data Architect in enterprise environments.
• Strong proficiency in Azure Cloud (Data Factory, Blob Storage, Synapse, AI Foundry, OpenAI).
• Advanced SQL and Python development experience.

Responsibilities

• Architect and implement end-to-end data pipelines and data warehousing solutions in Azure.
• Design and optimize ETL/ELT workflows using Azure Data Factory or equivalent.
• Collaborate with AI developers and cloud engineers to connect data pipelines to AI/RAG systems.

Skills

Cloud data migration

Data engineering

SQL

Python

Data orchestration

Mentoring

Tools

Azure Data Factory

Azure Blob Storage

Azure OpenAI Service

Vector databases

Job description

Data Solutions Architect job vacancy in Cape Town.

We’re seeking a Data Solutions Architect / Senior Data Engineer to join a growing Data and AI team working on an innovative cloud-based data warehousing and AI solution.

The team is developing a client-facing platform that integrates data warehousing with a RAG (Retrieval-Augmented Generation) system — transforming unstructured and structured data into organized, summarized, and insightful information for business use.

You’ll play a leading role in building out the production-ready environment, ensuring compliance, scalability, and performance, while contributing to the development of advanced AI-driven insights and automation capabilities.

High-Level Project Overview:

The platform focuses on the aggregation, synthesis, and summarization of unstructured data through a secure, scalable Azure-based architecture.

A proof of concept has already been built (a chatbot web app hosted on Azure), and the next phase involves expanding this into a fully integrated production solution.

Your work will involve:

• Designing and developing scalable data pipelines, storage, and processing components in Azure.
• Supporting the integration of RAG systems with AI models and vector databases.
• Enabling robust data flow between AI, search, and warehousing layers.
• Contributing to architectural decisions on performance, governance, and scalability.

Tech Stack:

• Framework / Orchestration: Azure AI Foundry (for AI workflow orchestration and management)
• LLM Provider: Azure OpenAI Service (designed to be model-agnostic for future extensibility)
• Storage: Azure Blob Storage Gen 2 (for documents and source data)
• Vector Store / Search: Azure AI Search (vector + hybrid search capabilities)
• App Hosting: Azure App Service (chatbot web app interface integrated with RAG)
• Embedding Model: Azure OpenAI text-embedding-3-large
• Data Warehousing: Azure Data Factory for data extraction, transformation, and integration between AI Foundry, AI Search, and Blob Storage

Key Responsibilities:

• Architect and implement end-to-end data pipelines and data warehousing solutions in Azure.
• Design and optimize ETL/ELT workflows using Azure Data Factory or equivalent.
• Collaborate with AI developers and cloud engineers to connect data pipelines to AI/RAG systems.
• Implement data models to support text retrieval, embedding, and summarization processes.
• Ensure compliance with data governance and security best practices.
• Mentor and support junior team members as the data capability scales.

Required Skills & Experience:

• 7+ years’ experience as a Data Engineer or Data Architect in enterprise environments.
• Strong proficiency in Azure Cloud (Data Factory, Blob Storage, Synapse, AI Foundry, OpenAI).
• Advanced SQL and Python development experience.
• Proven experience with cloud data migration and modern data warehousing.
• Knowledge of vector databases, AI model integration, or RAG frameworks highly advantageous.
• Understanding of data orchestration, governance, and security principles.
• Experience in insurance or financial services preferred.

Why Join:

This is a greenfield opportunity to help build a Data & AI capability from the ground up. The team currently consists of four engineers and is expected to grow rapidly in 2026. You’ll be working on cutting-edge Azure and AI technologies, shaping an intelligent platform that makes sense of large, messy datasets and transforms them into business-ready insights.