Junior Data Engineer: AI-Ready Data & Azure Pipelines

CSA Group, Architects and Engineers; San Juan (PR); On-site; USD 55,000 - 85,000; Full time

Job summary

CSA Group, Architects and Engineers is seeking a data-focused professional to design and optimize data models and pipelines for AI/LLM consumption in a fast-paced environment. You will work with Microsoft technologies to build AI-ready datasets and integrate APIs for robust data workflows.

The role emphasizes collaboration with stakeholders, governance, and responsible AI practices while supporting Power BI reporting and data quality initiatives.

Qualifications

• Bachelor’s degree in Computer Science or related field.
• 1–3 years of experience in a data-focused role or equivalent project portfolio.
• Experience cleaning, transforming, and structuring datasets (Excel, CSV, JSON, SharePoint, etc.).
• Basic knowledge of data pipelines (ETL/ELT).
• Working knowledge of Microsoft data tools (SharePoint, Power BI, Microsoft Fabric).
• Exposure to unstructured data (documents, PDFs, emails, etc.).
• Basic understanding of AI/LLM concepts (prompting, context design, RAG).
• Experience with APIs and data integrations.
• Familiarity with data modeling concepts (e.g., star schema, normalization).
• Experience supporting Power BI reporting environments.
• Understanding of data governance and data quality practices.
• Curiosity and interest in continuous learning in AI and comfort experimenting and iterating quickly; uses data to validate ideas and measure impact.
• Commitment to ethical and responsible AI adoption, including privacy‑by‑design and safe use of tools.

Responsibilities

• Design and implement data models, schemas, and structures optimized for AI/LLM consumption.
• Design and maintain data models, schemas, and pipelines (ETL/ELT) for structured and unstructured data.
• Develop and support data architectures within the Microsoft ecosystem (e.g., Fabric, Azure).
• Build and manage AI-ready datasets and context layers to support AI agents, Copilot solutions, and LLM workflows.
• Integrate data sources with APIs and AI frameworks, ensuring data accuracy, relevance, and performance.
• Collaborate with business stakeholders/SMEs to translate requirements into data models and AI-ready structures.

Skills

Data modeling

ETL/ELT

Power BI

Microsoft Fabric

APIs

Data governance

AI/LLM concepts

Structured/unstructured data

SharePoint

JSON/CSV

Education

Bachelor’s degree in Computer Science

Tools

SharePoint

Power BI

Microsoft Fabric

Job description

CSA Group, Architects and Engineers is seeking a data-focused professional to design and optimize data models and pipelines for AI/LLM consumption in a fast-paced environment. You will work with Microsoft technologies to build AI-ready datasets and integrate APIs for robust data workflows.

The role emphasizes collaboration with stakeholders, governance, and responsible AI practices while supporting Power BI reporting and data quality initiatives.