AI Developer with Python for Customer Care AI Platform team (f/m/d)

As an AI Engineer at IONOS, you will build core intelligence for a multimodal AI platform that connects real-time reasoning, context retrieval, and voice interactions. You will shape how AI acts on customer needs, not just chats, by integrating tools, orchestration, and RAG/CAG techniques. You’ll work with a cross-functional team to deliver low-latency, high-performance systems that scale across thousands of users and contracts. This role offers impact on a strategic, hybrid AI platform and opportunities to influence technology choices and workflows.

• training opportunities
• modern tech stack
• hybrid work option
• 25 vacation days
• meal tickets
• private medical package

• Design and implement LLM-based workflows with tool usage and MCP-based secure service interactions
• Develop high-performance RAG and Context-Augmented Generation pipelines with efficient context management and ranking
• Build and optimize real-time S2S pipelines focusing on latency, TTFW, and natural conversational flow
• Create automated QA and evaluation modules (LLM-as-a-judge) to measure accuracy, latency, and resolution at scale
• Integrate and optimize commercial and open-source models, balancing performance, cost, and use-case requirements

• Strong Python and/or Java engineering skills with asynchronous programming
• Experience with LLM-powered systems and multi-agent orchestration
• Familiarity with orchestration frameworks (e.g., LangChain, LlamaIndex, LangGraph)
• Deep understanding of vector databases and semantic search (Weaviate, Qdrant, pgvector, Elasticsearch)
• Experience with latency-aware, real-time systems and streaming architectures
• Knowledge of API design (REST, OAuth2)

• collaborative mindset
• ownership and initiative
• ability to translate evaluation insights into model improvements
• Python (asyncio, FastAPI)
• Java (production-grade services)
• LLM orchestration and multi-agent systems