(Senior) AI Engineer - Conversational AI Systems (m/w/d)

About your new role

We are building a conversational AI experience at idealo – a product-aware assistant that helps users explore, compare, and decide on purchases through natural dialogue. The system integrates capabilities like RAG-based access to product data, agent orchestration, and explainable result evaluation.

As an AI Engineer, you will combine conceptual thinking with hands-on engineering to design, implement, and evolve this AI-native experience. You will stay up-to-date in this dynamic field, continuously testing the latest AI developments and integrating them into production systems when they meet a real business need. You will work closely with our Fullstack Developers and AI Engineers, collaborating across the stack to deliver robust, scalable AI workflows that connect seamlessly with idealo’s product ecosystem.

• Build a sustainable, modular agent-style application that integrates existing components and conversational UIs.
• Develop and iterate frontend conversational formats (React, streaming/SSE) and connect them to backend services and prompt systems.
• Design, implement, and evolve agent architectures using common patterns and frameworks (e.g. Strands Agents, orchestrator/sub-agent designs on Amazon Bedrock AgentCore).
• Work with product search and retrieval pipelines to ensure relevant and up-to-date retrieval of product information.
• Develop and evaluate prompt flows – optimizing language quality, task alignment, and output stability.
• Define and monitor AI-specific non-functional requirements (e.g. hallucination rate, response quality, content safety, explainability).
• Stay on top of new AI capabilities, assess them critically, and integrate them into production systems when they add clear business value.
• Collaborate closely with product teams, Fullstack Developers, and MLEs to translate user and business needs into a flexible AI roadmap.

Skills & Requirements

• Proven experience building agent-style applications with real-world impact (LLM orchestration, tools, memory, autonomy).
• Hands-on knowledge of retrieval / RAG concepts and implementation (must).
• Track record in prompt engineering, prompt evaluation, and optimization strategies.
• Strong skills in both frontend development (conversational UIs) and backend orchestration (Python).
• Experience with retrieval architectures, context assembly, and vector stores.
• Ability to think conceptually and strategically about AI systems, while executing on technical implementation.
• Deep curiosity and initiative: you enjoy fast prototyping, experimentation, and iterative design.
• Bonus: Experience in AI system scaling, performance tuning, and quality assurance.