<p>Hey there! We're datin GmbH, and we are building the "new power grid" for scientific innovation.</p> <p>Traditional scientific knowledge is still largely hidden from LLMs because physical R&#x26;D data (like lab experiments, simulations, and equipment logs) is rarely recorded in a structured, machine-actionable way. Text alone isn’t rich enough to support automated discovery.</p> <p>To bridge this gap, we have built an ontology-driven, schema-based knowledge graph management system. Now, we are taking it to the next level: building autonomous, goal-oriented AI agents that can interact directly with our graph databases, augment them with new data, and identify emerging patterns in physical science.</p> <p>This role offers a unique opportunity to design production-grade AI agent systems from scratch, collaborating closely with experienced material scientists, tribologists, and software engineers. At datin, we value curiosity, impact, and trust, and we design our agent-driven workflows to empower scientists, not replace them.</p> <h2>Tasks</h2> <ul> <li><strong>Agentic Workflows:</strong> Design and build end-to-end agentic architectures. You will build tool-calling loops, memory layers, and execution environments that allow agents to query, update, and validate our graph databases.</li> <li><strong>AI Infrastructure:</strong> Engineer, deploy, and maintain performant agent and LLM serving infrastructures both locally and in the cloud.</li> <li><strong>Graph-Grounded LLMs:</strong> Fine-tune or optimize open-source LLMs to reliably translate natural language scientific requests into structured queries sent to our SDK and accurately traverse complex ontologies.</li> <li><strong>Machine Learning for Science:</strong> Train and integrate specialized ML models to solve multi-objective optimization problems (e.g., predicting material properties or chemical reactions) that AI agents can use as tools.</li> <li><strong>Semantic Digital Twins:</strong> Translate real-world physical workflows into semantically-typed knowledge graphs.</li> </ul> <h2>Requirements</h2> <ul> <li><strong>Technical Core:</strong> Deep practical experience with Agentic frameworks, orchestrators, or tool-use libraries.</li> <li><strong>Software Engineering:</strong> Strong proficiency in Python and/or JavaScript, with a focus on writing clean, modular, and well-tested production code.</li> <li><strong>Modeling Skills:</strong> Hands-on experience building, training, or fine-tuning models using machine learning frameworks like PyTorch or similar.</li> <li><strong>Validation:</strong> Familiarity with <strong>SHACL, RDF, RDFS, OWL, and SPARQL</strong> or similar (like <strong>CYPHER</strong>) validation languages is a strong plus.</li> <li><strong>Background:</strong> A degree in Computer Science, Information Science, or, Chemistry, Materials Science, Mechanical Engineering, or a related field.</li> <li><strong>Mindset:</strong> You are meticulous and logical. You enjoy solving the