Completed university studies (Master/Diploma) in the field of Chemical/Metallurgical/(Mineral) Process Engineering, Data Science, Statistics, Machine Learning or related field Good knowledge of mineral processing and statistics Familiarity with soft‑sensor concepts and data‑driven process monitoring Understanding of ore microstructures, particle characterization, and mineralogy Independent, self‑driven researcher with a strong problem‑solving mindset Proven team player, able to collaborate across multiple institutions Critical thinking to assess model performance, detect artefacts, and ensure scientific rigor Proficiency in Python (or Julia/R) for data handling, ML model development, and statistical analysis Ready to work with time‑series data, sensor fusion, and feature engineering Very good knowledge of English is mandatory, knowledge of German is an advantage

separation models to control flotation processes develop and implement soft‑sensor concepts for continuous monitoring of ore microstructures along the entire process chain using machine‑learning (ml) techniques and validate soft‑sensor outputs against laboratory reference measurements perform systematic laboratory flotation experiments (varying grinding and flotation conditions); collect and curate high‑frequency time‑series data train particle‑based separation models (psms), linking micro‑structural descriptors to flotation performance identify and evaluate online‑measurable proxies (exempli gratia, froth‑camera metrics, x‑ray fluorescence) for ore microstructures; conduct offline μxrf/tima analyses to simulate various xrf‑system configurations scale‑up and pilot‑test the developed concepts on a mini‑pilot flotation rig Document results and prepare scientific publications, conference presentations and project reports; contribute to the overall project work plan and milestones