Postdoctoral Researcher in AI-driven Surrogate Modeling for Manufacturing Process Optimization

Are you passionate about applying artificial intelligence to revolutionize traditional manufacturing processes? We are looking for a talented and motivated postdoctoral researcher to join our multidisciplinary team, working at the intersection of AI and mechanical engineering. In this exciting role, you will contribute to the development of innovative AI-based surrogate models that significantly accelerate forging process simulations, optimize manufacturing parameters, and reduce dependency on computationally expensive simulations.

This position offers the opportunity to work with leading experts, access state-of-the-art computational resources, and contribute to high-impact research that bridges academia and industry. If you have a strong background in AI, machine learning, and a keen interest in real-world applications, we encourage you to apply and be part of this exciting journey.

Manufacturing process optimization is a critical challenge in the modern industrial landscape, particularly in high-precision industries such as aerospace, automotive, and energy. Current methodologies in processes like forging rely heavily on computationally expensive simulations based on Smoothed Particle Hydrodynamics (SPH) or Finite Element Method (FEM), which require significant computational resources and expert knowledge. These traditional methods lead to prolonged development cycles and increased costs. The demand for rapid and accurate process optimization solutions is increasing, driven by the need to reduce time-to-market and production costs while maintaining high-quality standards.

This project aims to develop a novel AI-driven solution to revolutionize forging process optimization by leveraging surrogate modeling techniques. The objective is to create an AI-based tool that can:

• Accurately simulate forging processes in milliseconds instead of hours
• Predict optimal process parameters with high accuracy
• Reduce dependency on expensive simulations based SPH or FEM
• Enable real-time decision-making in production environments

• Design and implement data augmentation techniques to enhance model performance
• Implement efficient parametrization methods for geometries and workpiece properties such as temperature or strain
• Develop and optimize AI-based surrogate models for manufacturing processes
• Develop a user-friendly graphical interface (GUI) for interaction with the AI model, including real-time analytics and visualization
• Prepare manuscripts, reports, and presentations to disseminate findings
• Maintain thorough documentation of model development and project progress

Required

• PhD in Computer Science with the focus on AI
• Proficiency in python programming 
• Strong expertise in machine learning and deep learning frameworks (especially PyTorch)
• Demonstrated ability to work independently and as part of a multidisciplinary team
• Excellent written and verbal communication skills (Proficiency in English; German is a plus)

Preferred

• Basic familiarity with FEM and SPH
• Knowledge of manufacturing processes, especially forging
• Experience with computer graphics concepts such as implicit modeling, mesh processing, or CAD-related tasks
• Familiarity with reinforcement learning

The open position is in the Advanced Manufacturing Laboratory (Prof. Dr. Markus Bambach) within the Department of Mechanical and Process Engineering (D-MAVT) at ETH Zurich in Zurich, Switzerland.

We offer a 2-year project-based contract starting in Spring/Summer 2025 that includes:

• Opportunities to engage with different communities bridging machine learning and mechanical engineering leading to high impact publications
• You will be part of a highly motivated, multidisciplinary and collaborative team
• We will support your scientific career and application for postdoctoral fellowships on your path towards scientific leadership
• Access to state-of-the-art computational resources and collaborative research networks
• Opportunities for professional development and career advancement