{"@context":"https://schema.org","@type":"JobPosting","title":"Data Engineer H/F

We are looking for an AI Data Engineer to join Marketing & Sales Data Infrastructure team. In this role, you'll be working on use case driven by the AI Accelerator team.

In the age of Generative AI, Agentic AI, and Model Context Protocols (MCP), the Data Engineer plays a pivotal role in enabling intelligent systems to reason, act, and adapt based on rich, contextual data. You will build and maintain high-performance data pipelines and context-aware data systems that fuel autonomous agents and LLMs with precision, relevance, and scale.

This role requires a blend of traditional data engineering expertise with a deep understanding of how data is consumed by AI agents through protocols like MCP, enabling dynamic context injection, memory retrieval, and real-time adaptation.

You will collaborate closely with our existing Data Engineering teams and in-house Data Scientists, acting as a bridge between data sources and the advanced analytics and AI solutions being built.

What You'll do

• Data Preparation & Transformation: Clean, structure, and optimize datasets; build pipelines to ingest and serve trustworthy data for AI/ML applications.

• GenAI Optimization: Develop pipelines for GenAI use cases like RAG, fine-tuning, and prompt enrichment.

• Contextual Data Engineering: Build systems supporting Model Context Protocols for dynamic context injection into LLMs and agents.

• Data Governance & Documentation: Ensure compliance and data quality through contracts, lineage tracking, and clear documentation.

• Collaboration & Partnership: Work with Data Scientists and Engineering teams to align infrastructure with AI needs and strategies.

• Optimization & Scalability: Build scalable systems for large AI workloads and contribute to infrastructure decisions.

At least 5 years of experience in Data Engineering including contribution to GenAI projects

Fluency in English (required for our international environment).

Hard skills :

• Strong programming skills in Python, SQL, and distributed data frameworks.
• Fluency in using AI coding assistant like GitHub copilot, Claude code, Amazon Q developer, ...
• Experience with GenAI infrastructure (e.g., LangChain, LlamaIndex, RAG pipelines).
• Familiarity with MCP concepts and context management for LLMs.
• Hands-on experience with vector databases
• Knowledge of data mesh, data contracts, and modern governance practices.
• Familiar with cloud-native data platforms (e.g., AWS and Azure).

Soft skills :

• Clear, concise communication with Data engineers, Data scientist, Product owner, and Data stakeholders.
• Pragmatic mindset: balances engineering rigor with delivery.
• Ownership: pushes features from design through production with measurable outcomes.

"We passionately create enthusiastic customers and build a better future"​
Hilti is a global leader in providing technology-leading products, systems and services to the worldwide construction industry. Our success is driven by distinction, defying convention and powering some of the world’s most ambitious feats of engineering for our customers.
We are proud to be recognized as one of best workplaces on the 2020 Fortune 100 Best Companies to Work For® list and 2019 Best place to Work by Glassdoor, and ranked among the top employers by the Great Place to Work® Institute multiple times.