Sr. AI Engineer

We are looking for a seasoned Senior AI Engineer to design and implement advanced agentic AI systems capable of autonomously managing intricate workflows. This role involves architecting AI agents that can interact with diverse data sources, make informed decisions, and provide valuable, actionable insights to our clientele. This is a pioneering opportunity to lead enterprise-scale agentic AI implementation, setting new benchmarks for autonomous decision-making and intelligent automation within Deutsche Telekom. Key responsibilities include designing and deploying production-ready agentic AI systems for autonomous processing of customer documents and queries, architecting retrieval-augmented generation (RAG) pipelines for large-scale document management and information extraction, and implementing multi-agent orchestration frameworks for seamless coordination of specialized AI components. You will also develop robust context management systems for efficient and accurate handling of extensive customer data, create and optimize AI workflow automation for dynamic customer needs, and ensure AI system reliability, scalability, and regulatory compliance. Furthermore, you will implement comprehensive performance monitoring systems to evaluate AI output quality, accuracy, and relevance, and collaborate with cross-functional teams to integrate AI agents into existing business processes and systems. The ideal candidate will possess a minimum of 2 years of hands-on experience in developing and deploying agentic AI systems in production environments, with a proven history of building autonomous AI agents using frameworks like Langgraph, LlamaIndex, or ADK. Strong expertise in RAG architectures, vector databases, and document processing pipelines is essential, alongside experience in production AI deployment, monitoring, testing, and optimization. You should also have proven experience in designing quality metrics, feedback loops, and continuous improvement processes for AI systems, possess knowledge of enterprise-grade AI infrastructure and MLOps practices, and be familiar with AI safety, ethics, and compliance requirements.