19/10/2020

Postdoc in Machine Learning Model Development focused on Multiscale Materials Data

This job offer has expired


  • ORGANISATION/COMPANY
    Technical University Of Denmark
  • RESEARCH FIELD
    Computer scienceOther
  • RESEARCHER PROFILE
    First Stage Researcher (R1)
  • APPLICATION DEADLINE
    10/11/2020 12:00 - Europe/Brussels
  • LOCATION
    Denmark › Kgs. Lyngby, Copenhagen
  • TYPE OF CONTRACT
    Temporary
  • JOB STATUS
    Full-time
  • HOURS PER WEEK
    37

OFFER DESCRIPTION

The section of Cognitive Systems at DTU Compute, Technical University of Denmark (DTU) is looking for outstanding candidates for a 3-year postdoc position within the field of machine learning for developing models that can utilize multi source and multi fidelity materials data spanning orders of magnitude in length- and time-scale for both generative and predictive problems.

The research project is part of the European project BIG-MAP (Battery Interface Genome – Materials Acceleration Platform) under the large-scale, long-term European research initiative Battery 2030+ which seeks to reinvent the way we invent batteries using AI. The BIG-MAP consortium is coordinated by DTU and brings together researchers totalling 34 partners from 15 countries and spanning world-leading academic experts, research laboratories and industry leaders.

Project descriptions

The successful candidate will develop a range of machine learning algorithms working closely with other physicists, chemists and computer scientists to create a deep learning based Battery Interface Genome models for (inverse) design of batteries. The BIG-models are physics- and data-driven generative models to predict dynamic events at multiple time and length scales, e.g. from the atomic scale to the micron scale.

We will be developing machine learning algorithms, which can learn to map multi-scale battery interface dynamics into hierarchically coupled latent spaces that each encode for structures at different length scales. Furthermore, such a model will be integrated with a suitable time evolution propagator in the extended latent space to yield a complete dynamics simulator, which can be validated against multi-scale physics simulations of battery.

Additionally, the project aims at the autonomous discovery of chemical rules from large-scale data via semi-supervised learning and local descriptor search. Infusion of domain knowledge will be tried out to make the ML framework more data efficient.

To utilize data from multiple experimental and computational sources with varying levels of fidelity, we will use uncertainty propagation methods that are integrated within the models to take into account both data and model uncertainties.

The research is carried out in close collaboration with Professor and Section Head Tejs Vegge and Researcher Arghya Bhownik from Section for Atomic Scale Modelling and Materials at DTU Energy.

Qualifications

Candidates should have a PhD degree or equivalent. The PhD degree can be in machine learning or related fields. We are looking for candidates that preferably have a good research track record working in one or more of the following research areas:

  • machine learning and deep learning
  • mathematical modelling and computing
  • distributed data processing

In addition, you:

  • have a strong mathematical foundation, strong analytical skills
  • enjoy working with complex and unexplored (green field) topics
  • driven by pushing boundaries and courageous to try out new ideas building on previous expertise
  • track record of scientific publications and conference presentations
  • have the ability to work in cross-disciplinarily international team
  • experience with working in deep learning frameworks such as PyTorch.

Assessment

Professor Ole Winther and Researcher Arghya Bhowmik, DTU Energy will assess the applicants.

We offer

DTU is a leading technical university globally recognized for the excellence of its research, education, innovation and scientific advice. We offer a rewarding and challenging job in an international environment. We strive for academic excellence in an environment characterized by collegial respect and academic freedom tempered by responsibility.

Salary and appointment terms

The appointment will be for 3 years and be based on the collective agreement with the Confederation of Professional Associations. The allowance will be agreed with the relevant union. The employment is expected to start December 1, 2020 or shortly thereafter.

You can read more about career paths at DTU here.

Further information

If you need further information concerning this position, please contact Prof. Ole Winther at olwi@dtu.dk.

Application

Please submit your online application no later than 10 November 2020 (local time). Apply online at www.career.dtu.dk.

Applications must be submitted as one PDF file containing all materials to be given consideration. To apply, please open the link "Apply online", fill out the online application form, and attach all your materials in English in one PDF file. The file must include:

  • A letter motivating the application (cover letter)
  • Curriculum vitae
  • BSc/MSc/PhD diploma
  • List of publications indicating scientific highlights
  • List of References (at least two)

Applications and enclosures received after the deadline will not be considered.

All interested candidates irrespective of age, gender, disability, race, religion or ethnic background are encouraged to apply.

DTU Compute is an internationally unique academic environment spanning the science disciplines mathematics, statistics and computer science. At the same time, we are an engineering department covering informatics and communication technologies (ICT) in their broadest sense. Finally, we play a major role in addressing the societal challenges of the digital society where ICT is a part of every industry, service, and human endeavor.

The Section for Cognitive Systems is a lively and research-oriented group of scientists and support staff with a shared interest in information processing in man and in computers, and a particular focus on the signals they exchange - audio, imagery, behaviour.

Technology for people

DTU develops technology for people. With our international elite research and study programs, we are helping to create a better world and to solve the global challenges formulated in the UN’s 17 Sustainable Development Goals. Hans Christian Ørsted founded DTU in 1829 with a clear vision to develop and create value using science and engineering to benefit society. That vision lives on today. DTU has 12,000 students and 6,000 employees. We work in an international atmosphere and have an inclusive, evolving, and informal working environment. Our main campus is in Kgs. Lyngby north of Copenhagen and we have campuses in Roskilde and Ballerup and in Sisimiut in Greenland.

More Information

Work location(s)
1 position(s) available at
Technical University Of Denmark
Denmark
Kgs. Lyngby, Copenhagen
2800
Richard Petersens Plads Bygning 324

EURAXESS offer ID: 569177

Disclaimer:

The responsibility for the jobs published on this website, including the job description, lies entirely with the publishing institutions. The application is handled uniquely by the employer, who is also fully responsible for the recruitment and selection processes.

 

Please contact support@euraxess.org if you wish to download all jobs in XML.