Senior Data Engineer - Agentic AI

Senior Data Engineer - Agentic Ai

As the world's pioneering local delivery platform, our mission is to deliver an amazing experience, fast, easy, and to your door. We operate in over 70+ countries worldwide, powered by tech, designed by people. As one of Europe's largest tech platforms, headquartered in Berlin, Germany. Delivery Hero has been listed on the Frankfurt Stock Exchange since 2017 and is part of the MDAX stock market index. We enable creative minds to deliver solutions that create impact within our ecosystem. We move fast, take action and adapt. No matter where you're from or what you believe in, we build, we deliver, we lead. We are Delivery Hero.

We are on the lookout for a Senior Data Engineer – Agentic Ai to join the Vendor Data team on our journey to always deliver amazing experiences.

Our Vendor Data Team is building the data backbone powering intelligent, self-improving AI systems. As a Senior Data Engineer - Agentic Ai, you'll go beyond traditional ETL and pipelines into autonomous data orchestration. You will design the data interfaces that let AI reason, act, and improve: real-time data flows that fuel agent behavior, tools that enable AI-driven automation, and monitoring systems that ensure quality at scale. Your work won't sit in dashboards — it will ship into core AI-native products.

Our Agentic Ai team is redefining what data engineering means in the age of LLMs — enabling systems that access, evaluate, transform, and learn from data on their own. We treat LLMs as collaborators, not endpoints. Here, data infrastructure becomes a living system: dynamic retrieval, data-aware decision-making, and continuous evolution powered by feedback loops.

If you're ready to build the data layer for AI that builds AI — this is your playground.

Key Responsibilities

• Architect scalable data pipelines and retrieval systems enabling agentic reasoning and tool usage
• Build and operationalize RAG data flows — ingest, chunking, embeddings, indexing, and vector search optimization
• Develop APIs and data services that allow AI agents to interact with structured/unstructured vendor data in real time
• Monitor data quality, drift, and agent performance using automated evaluation and simulation agents
• Implement validation, observability, and governance to ensure safe, reliable AI behaviors
• Partner with AI and product engineering teams to deliver production-ready intelligence features

Qualifications

• 2+ years building production data systems in applied ML/AI environments
• Strong Python engineering skills — experience with LLM/RAG frameworks (e.g., LangChain, LlamaIndex, Haystack)
• Hands-on experience with vector databases (Pinecone, Weaviate, FAISS) and embedding pipelines
• Clear ownership mindset — you unblock yourself, navigate ambiguity, and deliver outcomes
• Bias toward action: ship fast, iterate responsibly, measure impact
• Pragmatic engineering: working, observable systems > perfect architectures

Nice to have:

• Familiarity with open-source model ecosystems (LLaMA, Mistral, Mixtral) or inference infra
• Experience with safety: prompt injection defense, output validation, agent guardrails
• Designed agent test harnesses or synthetic data systems for feedback loops
• Experience shipping AI-powered features in real-world data platforms, apps, or products