We are seeking an AI Engineer to join our team and specialize in developing LLM-powered (multi-)agents. In this role, you will design, build, and optimize intelligent agents that can reason, plan, and interact with both structured and unstructured data. You will work with large-scale language models (LLMs) and integrate them with tools, APIs, and external systems to create autonomous, reliable, and context-aware workflows. A key responsibility will be designing pipelines that prepare and structure information for LLM consumption—including retrieval, embeddings, and context optimization—so agents can perform multi-step tasks effectively. You may also design multi-agent systems for complex or multi-functional use cases that require collaboration between specialized agents. You will collaborate with cross-functional teams to push the boundaries of applied generative AI and deliver scalable AI-agent solutionsDesign and develop LLM-powered (multi-)agents capable of reasoning,  planning, and executing tasks across diverse domains.Build and maintain pipelines for data ingestion, knowledge retrieval, embeddings, and context optimization to make information consumable by LLMs.Integrate LLM agents with tools and APIs, enabling them to interact with external systems in real-world applications.Continuously improve and optimize pipelines for scalability, robustness, and performance in production environments.Benchmark agent performance and outputs, ensuring accuracy, reliability, and safety.Fine-tune and serve local LLMs and embedding models to support domain specific use cases and optimize inference.Conduct research and experimentation to advance capabilities in multi-agent systems, retrieval-augmented generation (RAG), and tool-augmented LLMs.Stay updated with state-of-the-art (SOTA) advancements in generative AI, agentic frameworks, and reinforcement learning with human feedback (RLHF)