Machine Learning Internship for Semiconductor Metrology

Introduction

Are you a student pursuing a master's in fields such as computer science, machine learning, computer vision, electrical engineering, mathematics, or physics? Do you have an affinity for Machine Learning and Deep Learning and a good understanding of Python and MATLAB? Then this internship is for you!

Background Information

ASML is a world leader in the semiconductor manufacturing industry. Our 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 optimizing 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 Image Processing & Machine Learning group within ASML caters to a wide range of algorithm-focused studies in the domain of wafer metrology.

Your Assignment

This software engineering internship comprises three different assignments. The hiring team will assess all applicants and allocate the assignments based on their needs. This will be further discussed during the interview stage.

First Assignment: Robust Pattern Recognition Algorithms for Semiconductor Metrology

The semiconductor manufacturing loop constantly involves imaging structures with nanometer-scale resolution. Among the wide range of algorithms used within ASML machines, pattern recognition (a 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.

Second Assignment: Machine Learning Algorithms for Optical Sensor Error Correction

The main goal of this internship assignment is to design and develop next-generation computational algorithms for sensor correction to eventually improve the performance of ASML's metrology systems. This project aims to create machine learning (ML) algorithms for optical sensor error correction. The ML model synthesizes metrology images given specific acquisition settings by learning the pixel-wise relationship within images.

Third Assignment: Next Generation Motion Deblur Algorithms for Semiconductor Metrology

The main goal of this internship assignment is to design and develop next-generation computational imaging algorithms (specifically motion deblur) to improve the system performance of ASML's metrology systems. Specific tasks will involve designing the signal processing pipeline for physics- and data-driven deblur algorithms which can be trained either offline or online.

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, or 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 apprentice internship with a duration of 6 to 12 months, for 4-5 days a week, starting as soon as possible.

Benefits

Monthly internship allowance of up to €600
Possible housing allowance
Free public transport
Practical guidance from experts in the field
Experience in a dynamic team environment

About ASML

ASML is a high-tech company headquartered in the Netherlands. We manufacture the complex lithography machines that chipmakers use to produce integrated circuits, or computer chips. What we do is at the heart of all the electronic devices that keep us informed, entertained, and connected. Every day, you use electronics that simply wouldn’t exist without our machines.