Postdoctoral Researcher in Physics Grounded Agentic AI for Power System Resilience Across Timescales

EPFL, the Swiss Federal Institute of Technology in Lausanne, is one of the most dynamic university campuses in Europe and ranks among the top 20 universities worldwide. The EPFL employs more than 6,500 people supporting the three main missions of the institutions: education, research and innovation. The EPFL campus offers an exceptional working environment at the heart of a community of more than 18,500 people, including over 14,000 students and 4,000 researchers from more than 120 different countries.

The Intelligent Maintenance and Operations Systems (IMOS) Lab at EPFL is looking for a motivated and out-of-the-box thinking postdoctoral researcher in Physics-Grounded Agentic AI for Power-System Resilience Across Timescales, starting in December 2026 or upon agreement.

Project Description

The objective of this project is to develop AI methods that strengthen power-system resilience across long-term infrastructure planning, operational decision-making, and disruption response. The research will investigate how infrastructure investments and adaptive operating strategies can jointly sustain critical services under uncertain disturbances, changing operating conditions, and component or communication failures.

The project will combine agentic AI with physics-informed learning, graph neural networks (GNNs), and multi-agent reinforcement learning (MARL).

• Physics-informed graph models will represent network interactions and support the assessment of grid behaviour across changing topologies and operating conditions.
• MARL will enable the coordination of distributed resources, including storage, generation, and flexible demand, under partial observability and communication constraints.
• Agentic AI systems will support structured reasoning by formulating and investigating disruption scenarios, coordinating simulation and optimization tools, and evaluating proposed interventions.

A particular emphasis lies on connecting planning and operation: understanding how adaptive operational capabilities influence the value of investments in network reinforcement, hardening, storage, and flexibility, and how planning decisions determine the options available during disruptions. Trustworthiness will be central, including uncertainty quantification, physical verification of proposed actions, transparent decision support, and robustness to previously unseen conditions. The precise research focus will be developed jointly with the successful candidate, building on their expertise and the lab's research strengths.

Work Environment

EPFL offers an exceptional international research environment with competitive salaries. The IMOS Lab (https://www.epfl.ch/labs/imos/) provides a highly motivating, interdisciplinary scientific environment with opportunities to interact across projects and researchers, and maintains an extensive network of collaborations with industrial stakeholders and leading international universities. The successful candidate will have opportunities to develop an independent research profile, contribute to doctoral supervision, and collaborate on methodological advances and power-system applications.

Candidate Profile

We are looking for a candidate with a strong analytical background and a PhD, completed or nearing completion, in Electrical Engineering, Computer Science, Control, Applied Mathematics, Operations Research, or a related field. You should have a solid foundation in machine learning or optimization, strong programming skills, and a demonstrated ability to conduct rigorous, independent research.

Strong expertise in machine learning is required, with demonstrated research experience in one or more of the following areas:

• Agentic AI, foundation models, or model-based reasoning.
• Graph neural networks, physics-informed learning, or hybrid modelling.
• Multi-agent reinforcement learning, constrained learning, or learning-based decision-making under uncertainty.

Experience in power-system modelling, planning, operation, or resilience is a strong asset. Candidates with a strong ML background and a clear motivation to develop methods for power-system applications are encouraged to apply. We expect the candidate to be self-driven, collaborative, and creative, with strong problem-solving abilities and out-of-the-box thinking. Professional command of English, both written and spoken, is mandatory.

Application Process

Formal applications should include:

• a letter of motivation.
• a CV of the candidate, including a publication list.
• A brief research statement (one page) outlining your research ideas on physics-grounded AI for power-system resilience and their connection to your experience and relevant literature.
• transcripts of all obtained degrees (in English).
• Contact details for two or three referees.

Applications should be submitted via the application platform. Further information on the EPFL IMOS Lab can be found at https://www.epfl.ch/labs/imos/.

Contract Start Date: December 1, 2026. Contract Type: CDD. Duration: 1 year renewable. Reference: 2572.