Physics | Data Science internship: physics modelling with machine learning

Introduction

Our group's mission is to deliver industrialized and optimal solutions to achieve a spectrally-pure collection of EUV radiation, enabling robust and efficient performance of the next generation of EUV photolithography machines. Our main responsibility lies in understanding and modeling the fundamental physical effects of the EUV source. This includes physical effects related to the generation of EUV radiation via a laser-driven tin plasma, efficient collection and transmission of this radiation, thermal effects within the EUV source, and the design and qualification of EUV optics, among others. To enable our work, we employ a wide range of commercial and in-house physical modeling applications/codes and we have a strong competence in fundamental physics, mathematics, scientific computing, machine/deep learning and data analysis.

Your Assignment

We are looking for two enthusiastic interns to join our team and help bring our models to the next level.
 

Assignment 1 is about: Merging Physics-Based Models with Deep Learning for Diagnostics

In this assignment, you will develop a hybrid model that integrates in-house, differentiable physics-based models, developed in Python, with deep learning algorithms to improve the diagnostic capabilities of the EUV optical system. The ultimate goal is to enhance the diagnostic capabilities of the EUV optical system, leading to a better fundamental understanding of physical processes and enabling preventative or corrective actions. Your tasks will involve:

• Conduct a literature review of state-of-the-art methods for merging physics-based models with deep learning;

• Develop a hybrid model that combines in-house, differentiable physical models with deep learning algorithms;

• Train the model using simulated or already existing experimental data;

• Validate its performance in diagnosing system issues;

• Investigate domain adaptation approaches to bridge the gap between simulated and real data;

• Collaborate with the team to industrialize the hybrid model;

• Document the findings and make proposals to improve system performance.

Assignment 2 is about: Temporal Modeling of Mirror Degradation in EUV Photolithography Systems

In this assignment, you will develop temporal models to predict the degradation of mirrors within EUV photolithography systems over time. The ultimate goal is to provide fundamental insights that help improve the performance of the EUV optical system. Your tasks will involve:

• Conduct a literature review of relevant physical principles and state-of-the-art models;

• Investigate physical mechanisms impacting mirror degradation and system evolution;

• Conduct in-depth exploratory data analyses and sensitivity studies using available datasets and existing in-house physics-based models;

• Build models to forecast the impact of mirror degradation on EUV system performance over various timescales;

• Utilize the newly-built model to predict degradation trends and propose mitigation strategies using a combination of data-based inference and physics-based knowledge;

• Validate and document the models and codes;

• Collaborate with the team to industrialize the models, so that they are accurate and reliable;

Both of these internships are suitable for a Bachelor/ Master internship for a minimum duration of 5-6 months (apprenticeship) and 9 months (graduation/thesis internship), working 4-5 days per week (3 days onsite). The start date of this internship is as soon as possible or at the latest around September.

Your profile

To be a fit for this assignment, you:

• Are busy with your bachelor's or master's in Physics, Mathematics or Computer/Data Science;

• Are skilled in Python (a must);

• Have an understanding of the fundamentals of machine learning;

• Have an affinity with physical-system modelling (a plus);

• Are enthusiastic about programming and working with data;

• Are good at problem solving and possess critical thinking skills;

• Have good communication skills in English (verbal and written).

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).

This position requires access to controlled technology, as defined in the United States Export Administration Regulations (15 C.F.R. § 730, et seq.). Qualified candidates must be legally authorized to access such controlled technology prior to beginning work. Business demands may require ASML to proceed with candidates who are immediately eligible to access controlled technology.

Diversity and inclusion

ASML is an Equal Opportunity Employer that values and respects the importance of a diverse and inclusive workforce. It is the policy of the company to recruit, hire, train and promote persons in all job titles without regard to race, color, religion, sex, age, national origin, veteran status, disability, sexual orientation, or gender identity. We recognize that diversity and inclusion is a driving force in the success of our company.

Need to know more about applying for a job at ASML? Read our frequently asked questions.