TU Delft

Helaas, deze vacature is niet langer actief

Originele vacaturetekst

PhD Material Design Under Uncertainty with Bayesian Deep Learning

Faculty Electrical Engineering, Mathematics and Computer Science

The Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) brings together three disciplines - electrical engineering, mathematics and computer science. Combined, they reinforce each other and are the driving force behind the technology we use in our daily lives. Technology such as the electricity grid, which our faculty is helping to make future-proof. We are also working on a world in which humans and computers reinforce each other. We are mapping out disease processes using single cell data, and using mathematics to simulate gigantic ash plumes after a volcanic eruption. There is plenty of room here for ground-breaking research. We educate innovative engineers and have excellent labs and facilities that underline our strong international position. In total, more than 1,100 employees and 4,000 students work and study in this innovative environment.

Click here to go to the website of the Faculty of Electrical Engineering, Mathematics and Computer Science.

Functie omschrijving

This position aims at fundamental developments of machine learning methods to design new materials under uncertain conditions. Materials Science sits between fundamental- and applied sciences because a new material needs to consider the entire process-structure-property chain. Unfortunately, real materials have uncertain properties and under the same conditions, two macroscopically identical materials exhibit stochastic values for the same properties. Machine Learning may offer methods to predict material characteristics under these uncertain conditions. The goal of this project is to develop Machine Learning models that incorporate physical knowledge and constraints to not only predict these material characteristics, but also their uncertainty. You will work on the necessary concepts and methodologies to learn models that can (1) predict material properties and (2) quantify the certainty in these properties. These models should adhere to physical constraints and have to be fitted to poorly sampled data as well as very large datasets. A possible approach could be to combine the concepts of deep learning with the Bayesian formalism, so that the very flexible deep learning models can be equipped with solid probabilistic reasoning.

The recently established “MACHINA” Artificial Intelligence Laboratory at TU Delft comprise members of the Faculty of Mechanical, Maritime and Materials Engineering and of the Faculty of Electrical Engineering, Mathematics and Computer Science. The MACHINA lab aims at bridging the gap separating ML developers (working in AI) from practitioners (working with AI) by a two pronged approach: (1) being a cradle for development of new AI methods that tackle nontrivial Materials Science and Solid Mechanics problems; and (2) promoting advances in the design and analysis of materials and structures recurring to adequate state-of-the-art AI methods. Questions about the MACHINA lab can be directed to Dr. Miguel A. Bessa (M.A.Bessa@tudelft.nl).

MACHINA is a Delft Artificial Intelligence Lab (DAI-Lab). Artificial intelligence, data and digitalisation are becoming increasingly important when looking for answers to major scientific and societal challenges. In a DAI-lab, experts in ‘the fundamentals of AI technology’ along with experts in ‘AI challenges’ run a shared lab. As a PhD, you will work with at least two academic members of staff and three other PhD candidates. In total, TU Delft will establish 24 DAI-Labs where 48 Tenure Trackers and 96 PhD candidates will have the opportunity to push the boundaries of science by using AI. Each team is driven by research questions which arise from scientific and societal challenges and contribute to the development and execution of domain specific education. Instead of the usual 4-year contract, you will receive a 5-year contract. Approximately a fifth of your time will be allocated to developing ground breaking learning materials and educating students in these new subjects. The experience you will gain by teaching will be invaluable for future career prospects. All team members have many opportunities for self-development. You will be a member of the thriving DAI-Lab community that fosters cross-fertilization between talents with different expertise and disciplines.

Functie eisen

  • A university Master of Science degree in computer science, electrical engineering, mathematics, physics or related area.

  • The ability to translate the requirements imposed by the applications of the group into a Machine Learning formulation, and translate back the Machine Learning results and limitations into the application relevant quantities.

  • Good writing and presentation skills in English, and certainly proficient in programming.

  • Initiative, drive and ability to setup, organise and execute your research.

  • An affinity with teaching and guiding students.

  • Demonstrable knowledge in current Machine Learning and Pattern Recognition methods is considered an advantage (related coursework, international competitions, personal development projects, etc).

  • Prior knowledge in mechanical engineering or materials science is not required, but there should be a strong interest in cooperating with colleagues in these areas.


TU Delft offers DAI-Lab PhD-candidates a 5-year contract (as opposed to the normal 4-years), with an official go/no go progress assessment after one year. Approximately a fifth of your time will be allocated to developing ground breaking learning materials and educating students in these new subjects.
Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from € 2395 per month in the first year to € 3217 in the fifth year. As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills. The TU Delft offers a customisable compensation package, discounts on health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. For international applicants we offer the Coming to Delft Service and Partner Career Advice to assist you with your relocation.

Informeren en solliciteren

For information about this vacancy, you can contact Dr. David Tax, Assistant Professor (Intelligent Systems), email: D.M.J.Tax@tudelft.nl, tel: +31 15 27 84232, or Dr. Miguel Bessa, Assistant Professor (Materials Science and Engineering), email: M.A.Bessa@tudelft.nl, tel: +31 (0)15 278 1933.

For information about the selection procedure, please contact Anita Lacroix, HR-advisor, email: A.Lacroix@tudelft.nl.

To apply, please email a letter of motivation, a detailed CV, an abstract of the Master thesis (1 page), preferred starting date, names of referees and MSc transcripts/Diploma (in English) in a single pdf file preferably before September 1st, 2020.

Please note that applications will be periodically reviewed also before the application deadline until a suitable candidate is found, therefore the position might be closed earlier. When applying for this position, please refer to vacancy number TUD00267. Please e-mail your application to Anita Lacroix, email: vacancies-eemcs@tudelft.nl.

A pre-employment screening can be part of the application procedure.

Acquisitie naar aanleiding van deze vacature wordt niet op prijs gesteld.

32-38 uur per week
Type vacature:


  • Er is geen minimale opleiding vereist
  • Voor deze functie is er geen minimale werkervaring vereist