imec logo
Contact
CMOS: advanced and beyond
Discover why imec is the premier R&D center for advanced logic & memory devices.
Integrated photonics
Take a look at technologies for optical transceivers, sensors and more.
Health technologies
See how imec brings the power of chip technology to the world of healthcare.
Sensing and actuation
Explore imec’s CMOS- and photonics-based sensing and actuation systems.
Connectivity technology
Look into our reliable, high-performance, low-power network technologies.
More expertises
Discover all our expertises.
Research
Be the first to reap the benefits of imec’s research by joining one of our programs or starting an exclusive bilateral collaboration.
Manufacturing
Go from idea to scalable and reliable semiconductor manufacturing with IC-Link.
Venturing
We create and co-create new ventures, and we invest in and accelerate existing ventures.
Education and workforce development
Imec supports formal and on-the-job training for a range of careers in semiconductors.
NanoIC pilot line
Aligned with the EU Chips Act, access to the pilot line will accelerate beyond-2nm innovation.
Semiconductor technology
Life sciences and health solutions
Data and telecommunication
Automotive technologies
Robotics technology for Industry 4.0
More applications
/Physics-Informed Machine Learning for Predictive MEMS Manufacturing

Physics-Informed Machine Learning for Predictive MEMS Manufacturing

PhD - Leuven | Just now

Combine machine learning, and semiconductor manufacturing to shape the future of MEMS technology.
Apply

Imec is a world-leading research and innovation hub in nanoelectronics and digital technologies, driving breakthroughs in semiconductor manufacturing, advanced sensing, and intelligent systems. Within imec’s MEMS activities, next-generation piezoelectric devices are being developed for applications ranging from healthcare and consumer electronics to industrial monitoring and communications

As demand for higher-performance MEMS devices continues to grow, manufacturing processes are becoming increasingly complex. Device performance and reliability are strongly influenced by process variations such as material properties, film thickness, stress, lithography accuracy, and equipment conditions. Understanding and controlling these interactions remains a major challenge, often requiring extensive experimentation and costly development cycles. 
 

A key challenge is to transform the vast amount of process and metrology data generated during MEMS fabrication into actionable knowledge. Existing machine learning approaches have shown promise but often struggle with limited data availability, noisy measurements, poor generalization, and a lack of physical interpretability. As a result, process optimization still relies heavily on expert knowledge and trial-and-error methods. 

In this PhD project, you will develop physics-informed machine learning models and digital twins capable of predicting MEMS device performance and manufacturing yield from fabrication and characterization data. By combining data-driven methods with physical understanding of materials, processes, and device behavior, you will create intelligent tools that help engineers identify critical process parameters, predict failures earlier, and accelerate technology development. 

The work will combine several aspects of research, including: MEMS fabrication and characterization, advanced data analytics, machine learning and artificial intelligence, digital twin development, uncertainty quantification, process optimization, and multiphysics modelling. You will collaborate closely with experts in MEMS technology, materials engineering, semiconductor manufacturing, and AI while leveraging imec’s state-of-the-art infrastructure and experimental facilities.

The ultimate goal is to establish a transferable and physically reliable framework that links manufacturing conditions to material properties, device characteristics, and final system performance. This framework will enable faster process development, improved yield prediction, reduced manufacturing costs, and a new generation of AI-assisted MEMS manufacturing technologies.
 

We are looking for a candidate with a strong interest in the intersection of semiconductor manufacturing, MEMS technologies, and artificial intelligence. The ideal candidate enjoys solving complex multidisciplinary problems using both experimental and computational approaches. 

A successful candidate should have:

  • A Master's degree in Electrical Engineering, Mechanical Engineering, Physics, Materials Science, Computer Science, Data Science, Applied Mathematics, or a related field. 
  • Strong analytical skills and a solid understanding of engineering, physical sciences, or quantitative modelling. 
  • Experience with programming and data analysis tools such as Python, MATLAB, or similar scientific computing environments. 
  • An interest in machine learning, artificial intelligence, statistical modelling, or data-driven decision making. 
  • Good communication skills and the ability to work effectively in a multidisciplinary research team. 

Since this topic is at the intersection of multiple technical domains, the ideal candidate should bring strong expertise in at least one of the following areas and be eager to develop skills across the others:

  • MEMS, semiconductor processing, microfabrication, or cleanroom technologies.
  • Machine learning, artificial intelligence, and modern data-driven modelling techniques.
  • Physics-based modelling, finite-element simulations, digital twins, or multiphysics tools.
  • Data analytics, predictive modelling, uncertainty quantification, or experimental data interpretation.

You do not need to be an expert in all these domains from day one. This PhD offers a unique opportunity to combine advanced manufacturing, MEMS technology, and AI research while developing expertise across multiple disciplines. 
 


 


 


 

Required background: Electrical Engineering, Mechanical Engineering, Physics, Materials Science, Computer Science, Data Science, Applied Mathematics, or equivalent.

Type of work: 50% Modeling, 30% Experimental, 10% Data Analytics, 10% Literature Review & Scientific Dissemination

Supervisor: Michael Kraft (KU Leuven)

Co-supervisor: Michael Kraft (KU Leuven)

Daily advisor: Guilherme Brondani Torri, Milind Narasimha Pandit, Alexey Podkovskiy

The reference code for this position is 2027-150. Mention this reference code in your application.

Apply
Who we are
Accept analytics-cookies to view this content.
imec's cleanroom
Accept analytics-cookies to view this content.

Related jobs

Ternary-blend Halide Perovskites for Thin-Film Photonic Devices: From Photodetectors to LEDs and Lasers

From material discovery to laser light: engineering next-generation perovskites

Organic Chiro-Optical devices

Design and fabricate opto-electronics sensitive to the helicity of photons.

Oxygen-Controlled Printing and Interfacing of Liquid Metals for Reliable Robotic Electronic Skins

What if the very thing that makes liquid metals printable is also what limits their reliability?

Hetero-integration of two-dimensional electronic materials for active memory applications

Explore ways to build digital memory with molecularly thin films to meet the computing needs of the future

Thin-Film Ga₂O₃ for Next Generation Deep-UV Sensing

Building the First CMOS-Compatible Solar-Blind Imagers Based on Gallium Oxide

Deterministic Robotic E-Skin Networks

Reimagining Ethernet TSN as the nervous system technology for future robotic e-skins, enabling distributed sensing, local reflexes, and deterministic intelligence on flexible/stretchable electronic substrates.
Job opportunities

Send this job to your email