Job Details



Refer Job: Send to a Friend
  • Share this on Facebook
  • Share this on LinkedIn

Add Add to Saved Jobs

Back

Data-Science and Statistics Researcher

Location Veldhoven, Netherlands
Level Master
Experience 2-5 Professional
Functional Area Research & Development    
Background Mathematics  Physics  
Travel No
Reference req6024

Introduction

Are you challenged by demanding projects in a multidisciplinary context? Do you have the technical capabilities to provide innovative, data-driven and statistical solutions in an industrial research context? Does contributing to the world’s most advanced lithography machines makes you feel responsible and proud? Then this might be the right opportunity for you.

Job Mission

ASML Research is looking for a Data Scientist to join and further develop the Data-science and Machine Learning  group. The Data-science and Machine Learning group focus is on data-driven and statistical parameter inference technology to analyze, optimize and control the performance  of future and existing Lithography Tools. This covers combining Knowledge about the system with data from the system to find novel solutions for Fault Detection and Isolation, Predictive Maintenance, Drift Detection and Compensation. All this, for systems which belong to the most complex systems on earth.

Job Description

As Data-science and Statistics expert, your work will consist of:

- Apply and develop methodologies and models to capture knowledge.

- Apply and develop state of the art machine-learning, statistics and information-theoretical methods that support identification of abnormal system-behavior and data relations.

- Work closely with domain experts to find, validate and understand causal relations.

- Ensure knowledge sharing at various levels in the organization and with colleagues from different disciplines.

- Support in identifying ‘best in class’ existing technologies, and high-potential, ‘beak-through’ new approaches.

- Provide guidance for (junior) data scientists in how to apply advanced data-science methods depending on the nature of the problem, the expected insights to be gained and the quality of
the available data.

- Build and maintain network with external research institutes and universities. 

Education

- PhD ( preferably ) in Data Science, Machine Learning, Mathematics or  a related field, with dominant Data Science or Machine Learning component or Master in Engineering/ Physics  with  2-5 years relevant experience in Machine learning in academic or industrial research  environment.

Experience

- Experience in defining effective solution directions given a data challenge.
- Broad knowledge of available tools, algorithms, and experience in how to apply them.
- Preferably experience in data-analysis related to complex systems, i.e. in the direction of anomaly detection or predictive maintenance.
- Strong pre if experience in a.o. Matlab and Python for machine-learning problems.

Personal skills

- Open to learning techniques outside of the above mentioned fields in the future. 
- Autonomously identify relevant challenges and (new) solution directions.
- Inquisitive and strong personality.
- Pragmatic attitude with an analytical view.
- Able to communicate effectively across disciplines and at all organizational levels.
- Fluency in English.

Context of the position

The new Data-science and Machine Learning group is part of the Research department of ASML. Its task is to identify and fill in the technological gaps in the future roadmap of lithography and the lithography market. Our focus is on applying advanced data-science technology to add value on top of existing and future lithography systems by improving system performance and reliability. We work in small teams and deliver proof of concept solutions that can be transferred to Development and Engineering. We intensively work together with external research institutes
and universities.  


Other information

Keywords:

Industrial research, data-science, machine-learning, statistics, statistical parameter inference, information-theory, predictive maintenance.