Machine learning internship: robust pattern recognition algorithms for semiconductor metrology

ASML is a world leader in the semiconductor manufacturing industry. It's innovative machine stack includes state of the art lithography systems along with cutting edge metrology systems such as Yieldstar. In semiconductor manufacturing overlay is defined as the spatial alignment error between two semiconductor layers. The control of overlay plays an essential role in the optimization of the fabrication yield and profit margin. In this project, you will have the opportunity to interact with various experts on optics and signal processing in the context of YieldStar. The group Image Processing & Machine Learning within ASML caters to a wide range of algorithms focused studies on the domain of wafer metrology. 

Your Assignment:

The semiconductor manufacturing loop constantly involves imaging structures with nanometer scale resolution. Among the wide range of algorithms used within ASML machines,  pattern recognition (well-known computer vision algorithm) plays a key component in the processing pipeline. The main goal of this internship assignment is to design and develop next generation pattern recognition algorithms to improve the performance of ASML's metrology systems. Specific tasks will involve designing the signal processing pipeline for physics- and data-driven pattern recognition algorithms. The developed algorithms will be tested on both simulated and measurement data of structures imaged using ASML's Yieldstar system.  The starting point will involve constructing a robust signal processing pipeline on images with partially known target templates. The candidate is expected to perform a detailed and systematic comparison of the current methods (where target template is a hard constraint) with the techniques developed in the project. 

Your Profile

To be a perfect match for this internship, you:

• Are a Master student in the field of computer science, machine learning, computer vision, electrical engineering, mathematics and physics.

• Have experience with Signal Processing, Machine Learning, Deep Learning, Hybrid-Machine Learning and Physics Inspired Neural Networks.

• Have a good understanding of Python and MATLAB.

• Have demonstrated an interest in or have experience with hybrid approaches where domain knowledge is incorporated into Machine Learning/Deep Learning models.

• Have great communication skills in English both verbally and in writing.

This is a Master industrial internship with a duration of 6 to 12 months, for 5 days a week, starting as soon as possible. Note that this project is not meant for those who are intending to pursue a thesis project. However, there could be a possibility to extend the scope of the project into a thesis project after the completion of the industrial project.

Other requirements you need to meet

• You are enrolled at an educational institute for the entire duration of the internship;

• You are located in the Netherlands to perform your internship. In case you are currently living/studying outside of the Netherlands, your CV/motivation letter includes the willingness to relocate;

• If you are a non-EU citizen, studying in the Netherlands, your university is willing to sign the documents relevant for doing an internship (i.e., Nuffic agreement).