Magnet.me  -  Het slimme netwerk waar studenten en professionals hun stage of baan vinden.

Het slimme netwerk waar studenten en professionals hun stage of baan vinden.

Computer science | machine learning | AI internship: twinscan fiducial measurement

Geplaatst 29 sep. 2025
Delen:
Werkervaring
0 tot 2 jaar
Full-time / part-time
Full-time
Functie
Opleidingsniveau
Taalvereiste
Engels (Vloeiend)
Startdatum
1 februari 2026

Je carrière begint op Magnet.me

Maak een profiel aan en ontvang slimme aanbevelingen op basis van je gelikete vacatures.

Be part of progress

Introduction

The MX (Metrology and Machine Control) cluster provides the supervisory control, modelling and optimisation algorithms to the Twinscan range of platforms. Within this cluster, the levelling department is responsible for vertical measurement of the wafer surface relative to fiducials in the system.

As part of the operation of the Twinscan, there are fiducial plates that are measured every time a new wafer is loaded, to ensure the position of the sensors relative to the wafer chuck. However, at the nanometer scale, these plates can become contaminated, and also microscopic water droplets can be left on them by the immersion system. In order to get the best positional measurement, these undesired effects must be identified and removed. While we have an algorithm that performs this, we are always looking for improvements.

In this internship, you will work with domain experts to investigate the use of a Deep Learning Surrogate (DLS) in place of the current algorithm.

Key deliverables include:

  • The design and training of the DLS model, using real or synthesised data as appropriate.
  • Benchmarking against the current non-ML algorithms.
  • Investigation of the integration into the current (C++) Twinscan environment, with topics such as diagnostics capabilities, data mapping, control logic, process deployment, updates of weights in an industrial environment, compute resource requirements, and more.

This is a (preferably) master or university bachelor internship (also suited for a thesis internship) for a minimum of 5 months, minimum 4 days per week (2-3 days on-site). The start date of this internship is February 2026 (or sooner).

Your profile

  • Background in Computer Science, Machine Learning, AI or related fields.
  • Experience with Python, PyTorch / Tensorflow, and C++.
  • Familiarity with MATLAB is a bonus.
  • Professional communication and documentation skills: able to explain and present technical matters within the team.
  • Pragmatic, pro-active, self-propelling way of working and able to operate in a dynamic environment.

Other requirements you need to meet

  • You are enrolled at an educational institute for the entire duration of the internship.
  • You need to be located in the Netherlands to perform your internship. If you are currently living/studying outside of the Netherlands, your CV/motivation letter should include your willingness to relocate.
  • If you are a non-EU citizen studying in the Netherlands, your university must be willing to sign the documents relevant for doing an internship (i.e., Nuffic agreement).

About ASML

ASML is a leading supplier of lithography equipment, used by the world’s top chipmakers to print microchips that are increasingly powerful, fast and energy efficient. Working at ASML is inspiring, no matter what field you're in. That’s because we push the boundaries of technology: if it’s moving the world forward, chances are, we’re behind it. In fact, we’re probably a part of the electronic device you’re using right now. We’re a global team of more than 32,000 people from 122 different nationalities and counting. Headquartered in Europe’s top tech hub, the Brainport Eindhoven region in the Netherlands, our operations are spread across Europe, Asia and the US.

We're moving technology forward
In fact, we’re probably a part of the electronic device you’re using right now. Our lithography technology is fundamental to mass producing semiconductor chips. With it, the world’s top chipmakers are creating microchips that are more powerful, faster and energy efficient.

Engineering
Veldhoven
Actief in 16 landen
42.000 medewerkers
70% mannen - 30% vrouwen
Gemiddeld 38 jaar oud