Digital/Data Engineer with AI (Poland)

What you will do

— Design and deliver digital solutions with a primary focus on GenAI (70% of the role) and process automation (30%).
— Build and deploy POCs (Proof of Concepts) for chatbots, RAG (Retrieval-Augmented Generation) systems, and document analysis tools.
— Work side-by-side with traders and business teams to observe workflows and spot inefficiencies.
— Integrate existing enterprise LLMs (ChatGPT, Claude) via APIs into the project's ecosystem.
— Use Python and SQL for rapid scripting, data manipulation, and automation.
— Leverage platforms like Azure Databricks (Mosaic), Copilot Studio, and internal tools (Foundry/Mosaic).
— Develop and optimize ELT/ETL pipelines using tools like Databricks, Data Factory, Glue, or Airflow
— Model and maintain structured and semi-structured data for analytics, AI, and automation use cases
— Translate business problems into clearly defined digital or AI use cases with measurable value
— Support risk assessment, compliance, and governance processes for data and AI solutions
— Present findings and insights to business users; act as a Subject Matter Expert for data architecture
— Mentor junior engineers and contribute to engineering excellence within the team
— Ensure solutions are secure, scalable, and aligned with Shell’s data and AI architecture standards

What we expect

— 8+ years of experience in Data Engineering, Software Engineering, or a related technical field.
— Hands-on GenAI Expertise: Proven track record of delivering production-ready GenAI solutions (LLM integration, RAG workflows, and advanced Prompt Engineering).
— Experience with Azure Databricks (Mosaic), Copilot Studio, and internal tools (Foundry/Mosaic)
— Exceptional stakeholder management and storytelling skills. You must be able to lead discussions with business leaders, translate pain points into technical requirements, and demonstrate value.
— Strong proficiency in Core Python and SQL.
— Deep experience with ELT/ETL processes, data modeling, and ingestion tools (e.g., Azure Data Factory, Databricks, Synapse, Airflow).
— Familiarity with modern AI frameworks and platforms like LangChain, LangGraph, Databricks Mosaic, and AI Foundry.
—Solid experience with Azure (preferred) or AWS, including CI/CD pipelines (GitHub Actions, Azure DevOps) and testing (PyTest).
— Strong understanding of data architecture, modern data platforms, and handling unstructured data for AI-enabled pipelines.
— Comfortable working in fast-paced, iterative Agile environments (Scrum/Kanban) to deliver POCs and Quick Wins.
— Fluent English for seamless daily collaboration with global teams.
— Based in Kraków with a commitment to working from the office 2–3 days a week to maintain close alignment with the business.