PhD Student in Deep Domain Adaptation for Fleet Knowledge Transfer

The newly founded Intelligent Maintenance and Operations Systems (IMOS) Lab at EPFL has a PhD researcher opening, 100% Lausanne, fixed-term, starting as soon as possible or upon agreement.

PROJECT DESCRIPTION

The goal of the project is to develop predictive maintenance algorithms for diverse fleets of technical equipment that enable to transfer operational experience and fault patterns between different units benefitting from the fleet knowledge, improving the robustness and enabling continual learning and improvement. The goal is to develop a framework that enables a distributed and automated adaptation of the algorithms to new systems, new operating conditions and new fault types.

WORK ENVIRONMENT

EPFL is one of the most dynamic university campuses in Europe and ranks among the top 20 universities worldwide and offers an exceptional working environment with very competitive salaries. The IMOS Lab offers a highly motivating, interdisciplinary scientific environment with many opportunities to interact between different projects and researchers, and has an excellent network of collaborations with industrial stakeholders and other international universities.

CANDIDATE PROFILE

We are looking for a PhD candidate with a strong analytical background, and an outstanding MSc degree in Engineering, Control, Computer Science, Physics, Applied Mathematics, or a related field. You should be proficient in machine learning, deep learning, geometric deep learning, signal processing, statistics and learning theory. 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.

APPLICATION PROCESS

Formal applications including :

  • a letter of motivation,
  • a CV of the candidate,
  • brief research statement (one page) describing your project idea in the field of physics-informed deep learning algorithms, making connection to your experience in this area and the related work from the literature,
  • transcripts of all obtained degrees (in English)
  • one publication (e.g. thesis or preferably a conference or journal publication, providing a link to the publication is sufficient),

should be sent via email (as a single pdf file) at [email protected] before 31.07.2022.  For technical questions, please contact Prof. Dr. Olga Fink at [email protected]

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