This PostDoc position is offered in collaboration with the Intelligent Maintenance and Operations Systems (IMOS) Laboratory at EPFL, and Urban Energy Systems Laboratory (UESL) at EMPA.
Application link: https://apply.refline.ch/673276/2121/pub/1/index.html
Key qualifications include:
- Strong research experience in deep learning and foundation models, including experience with pre-trained models, fine-tuning, transfer learning, or self-supervised learning. Experience with tabular foundation models or foundation models for structured data is particularly relevant.
- A strong understanding of modern deep-learning architectures and training strategies, and experience designing and rigorously evaluating new machine-learning methods. • Excellent Python programming skills and strong hands-on experience implementing, training, and evaluating deep-learning models and research codebases.
- A strong track record in machine learning or closely related fields
- Excellent written and spoken English
Ideally, the candidate also:
-
Has experience in energy system modeling and optimization
-
Has experience with tabular or heterogeneous data, particularly across multiple da-tasets, domains, or tasks
-
Is familiar with mathematical optimization methods, such as mixed-integer linear programming
-
Has experience with uncertainty quantification, surrogate modelling or physics-informed machine learning
-
Has an understanding of the technical challenges associated with the energy transition
The Intelligent Maintenance and Operations Systems Lab at EPFL is looking for a motivated and out-of-the-box thinking PhD researcher.
Application link (please use a different browser if it doesn’t open): https://careers.epfl.ch/job/Lausanne-PhD-Student-in-Trustworthy-AI-for-Autonomous-Plant-Operations/1165540855/
PROJECT DESCRIPTION
The objective of this project is to develop a trustworthy AI framework for the autonomous operation of process plants. The research will focus on AI agents that monitor the plant state, detect and diagnose abnormal situations, and recommend or execute operating actions, while meeting the safety, reliability and transparency requirements of safety-critical environments.
The project will explore how learning-based and agentic AI systems (e.g., agents built on large language or foundation models) can be combined with physics-informed process models, digital twins and engineering knowledge such as P&IDs and operating procedures. A particular emphasis lies on trustworthiness: quantifying uncertainty, verifying agent decisions before they reach the plant (e.g., doer–checker architectures), explaining recommendations to operators, and remaining robust to sensor faults, distribution shifts and previously unseen operating conditions. Applications will include complex process plants, where autonomous decisions directly affect safety, product quality and asset lifetime.
We are looking for a PhD candidate with a strong analytical background and an outstanding MSc degree in Computer Science, Robotics, Chemical/Process, Mechanical or Electrical Engineering, Control, Applied Mathematics, or a related field. You should have a solid foundation in machine learning and strong programming skills (Python, deep learning frameworks such as PyTorch), ideally with experience in one or more of the following: large language models and agentic AI, uncertainty quantification, anomaly detection and fault diagnosis, or decision-making under uncertainty.Prior experience with process systems engineering or process control, physics-informed or hybrid modeling, explainable AI, or the verification and safety assurance of learning-based systems is considered a strong asset, as is experience with industrial time-series data or process simulators.We expect the candidate to be self-driven, with strong problem-solving abilities and out-of-the-box thinking. Professional command of English (both written and spoken) is mandatory.