Ai data engineer
Summary
PBT Group is hiring an AI Data Engineer in Cape Town to design data migration and modernisation pipelines that use AI agents for data discovery, schema mapping, transformation, validation and data quality. Core stack: Python, SQL, ETL/ELT, cloud data platforms (AWS/Azure/GCP) plus LLM and agentic tooling like LangChain and RAG.
We are looking for an AI Data Engineer – Migration to join a specialist data modernisation initiative, combining traditional Data Engineering with emerging AI and agentic technologies.
The role will focus on using AI-assisted and agent-based solutions to support complex data migration and modernisation, including data discovery, schema mapping, transformation, validation and data-quality processes.
We are not looking for an exact technology match. Strong Data Engineering experience combined with practical exposure to AI, LLMs or agentic development will be considered.
What You’ll Be Doing: Design and develop data migration and modernisation pipelines. Work with AI agents to automate data discovery, schema mapping, transformation and validation. Integrate AI/agentic workflows with traditional Data Engineering platforms and tools. Analyse legacy data structures and support migration to modern cloud environments. Build data-quality, validation and human-in-the-loop processes. Develop and integrate APIs and data services. Work with technical teams to ensure solutions are scalable, reliable and secure. Apply AI-assisted development tools while reviewing and validating generated outputs. Support data governance, security and privacy requirements.
What We’re Looking For: A Bachelor’s or Master’s degree in Computer Science, Data Engineering, Artificial Intelligence, Information Technology or a related field would be advantageous. 3+ years’ experience in Data Engineering. Strong Python and SQL skills. Experience with ETL/ELT pipelines and data transformation. Experience with a cloud data environment such as AWS, Azure or GCP. Exposure to AI, LLMs, Generative AI or AI agents. Experience with APIs, microservices, Docker or CI/CD would be advantageous. Strong analytical and problem-solving ability. Comfortable working with complex or legacy data environments. Ability to work independently and collaborate with technical and business stakeholders. AI / Agentic Experience Exposure to technologies such as the following would be advantageous: Lang Chain / Lang Graph Auto Gen / Crew AI / Llama Index Open AI / Anthropic / other LLM APIs Prompt engineering and structured outputs RAG / Vector Databases AI-assisted coding and development tools
You do not need experience across all of the above. We are particularly interested in candidates who understand the concepts and have hands‑on exposure to applying AI within Data Engineering or software development.
Advantageous Experience: Legacy‑to‑modern data migration or application modernisation. AWS, Azure or GCP data platforms. Spark / Py Spark, dbt, Airflow, Snowflake, Big Query or Databricks. Experience working with legacy relational, mainframe or No SQL data. Data quality, testing and validation frameworks. Experience implementing AI solutions within regulated or enterprise environments.
Why Join?
This is an opportunity to work at the intersection of Data Engineering, AI and modernisation, contributing to practical solutions that use emerging agentic technologies to solve complex data migration challenges. #J-18808-Ljbffr