Summary
Robert Kräuter is a machine learning engineer specializing in pharmaceutical process engineering, bringing a decade of experience applying data-driven models to complex physical systems. He blends academic rigor from a mechanical engineering background and hands-on research in turbulent convection with practical industry impact, most recently building digital twins and ML-driven control for pharma processes at Glatt Group. His work spans recurrent and convolutional neural networks, transient flowsheet simulation, and CFD-based performance improvements, demonstrating an ability to bridge high-fidelity physics models and production-ready ML solutions. Robert has a track record of improving process understanding—e.g., using RNNs to reconstruct sparse experimental flow fields and delivering 10-15% airflow gains during CFD-driven refrigeration R&D. Based in Weil am Rhein, he combines experimental data expertise with software implementation skills (Python/TensorFlow/OpenFOAM) to make measurable engineering improvements. Colleagues value his pragmatic approach to turning turbulent, noisy measurement data into actionable process control strategies.
10 years of coding experience
Dipl.-Ing., Mechanical Engineering, Dipl.-Ing., Mechanical Engineering at Technische Universität Ilmenau