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 17,000 people, including over 12,500 students and 4,000 researchers from more than 120 different countries.

Postdoctoral Researcher in Physics-Informed ML and GNN for Industrial Time Series Data

Mission

The Laboratory of Intelligent Maintenance and Operations Systems focuses on developing intelligent algorithms to improve performance, reliability and availability of complex infrastructure and industrial assets and making the maintenance more cost efficient. Our research spans a range of cutting-edge techniques, including physics-informed machine learning, domain adaptation, (physics-informed) graph neural networks, and deep reinforcement learning, specifically applied to the unique challenges of complex industrial and infrastructure systems. We work primarily with heterogeneous, multivariate time series data characterized by varying data types, sampling rates, and degrees of uncertainty.

EPFL is one of Europe’s most dynamic university campuses, consistently ranked among the top 20 universities worldwide, and provides an exceptional working environment with highly competitive salaries. The IMOS Lab offers a stimulating, interdisciplinary research environment with extensive opportunities for collaboration across diverse projects and researchers. Additionally, the lab maintains a strong network of partnerships with industry stakeholders and leading international universities, enriching both research impact and professional development.

Profile

We are seeking a highly motivated and talented Postdoctoral Researcher to join our dynamic team. The successful candidate will play a key role in developing models that capture the dynamics and degradation of industrial and infrastructure assets using Physics-Informed Machine Learning (PIML) and (Physics-Informed) Graph Neural Networks (GNNs). This position offers a unique opportunity to lead pioneering research, drive innovation, mentor students, and collaborate closely with industrial partners.

Ph.D. in Computer Science, Machine Learning, Data Science, Signal Processing, or a related field. The ideal candidate should have a solid academic foundation and demonstrated expertise in deep learning, particularly with experience in Physics-Informed Machine Learning (PIML) and/or Physics-Informed Graph Neural Networks (GNNs).

Research Experience: Proven ability to conduct independent, cutting-edge research in deep learning, specifically in (Physics-Informed) GNNs and PIML, with a track record of publications in high-impact journals and top-tier machine learning conferences.

Mentorship Skills: Strong interpersonal and communication skills, with the ability to effectively mentor and guide students.

Innovative Mindset: I Independence, curiosity, and innovation are highly valued qualities in the successful applicant. We encourage creative thinking and the exploration of novel research directions.

Key responsabilities

Research Leadership: Lead research projects focused on developing advanced models that capture the dynamic behavior and degradation of complex assets. This includes advancing deep learning techniques, such as GNNs and PIML algorithms, to create innovative solutions for intelligent maintenance and operation of complex systems. Responsibilities include conducting experiments, developing novel algorithms, and publishing research in top-tier journals and conferences.

Mentorship: Independently supervise master’s students and contribute to the supervision of PhD students, supporting their academic and research development.

Teaching: Minimal teaching responsibilities, with a primary emphasis on research and mentorship.

Application Process

The application file should contains:

  • a letter of motivation,
  • a detailed CV including a list of publications and awards (if applicable)
  • a short research statement (1-2 pages) outlining the intended research proposal, making connection to your experience in this area and the related work from the literature,
  • scanned transcripts of all obtained degrees (in English) (Doctorate, Master’s degree, other degrees)
  • The names and email addresses for 2-3 individuals who can provide reference letters.

Informations

Application deadline:  09.12.2024

Further information on EPFL IMOS Lab can be found under: https://www.epfl.ch/labs/imos/

Activity Rate  : 100% 

Contract Type: CDD

Duration: 1 an, renouvelable 

Reference: 1195 

Shortlisted candidates will be invited to apply to one of the EPFL doctoral schools (e.g. EDEE). This parallel application process is necessary to be eligible for a PhD at EPFL.