Python Job: Data Scientist

Role and responsibilities

• Support in formulating problem statement and performing exploratory data analysis to identify trends and patterns. Develop functional prototypes and document these through technical specifications. Able to tell a story with data and convince stakeholders.
  
• Define industrialization requirements that support the deployment of the data and analytics models, including test based specification towards the IT development teams (based on unit tests and metrics).
  
  • Generate, own and manage the CS data model as the one source of truth based on trusted and current data and align with the data architects
    
  • Apply leading analytics tools (e.g. Python, Alteryx, Spotfire) and technologies to develop in-depth understanding of structured and unstructured data on the topic at hand
    
  • Use ETL tools to apply data cleansing and transformation techniques for prototypes and describe data quality metrics for industrialization
    
  • Apply predictive models and evaluation criteria based on applicable metrics
    
  • Generate business insights by translating data into visuals, reports and dashboards.
    
  • Interact with technical and non-technical (cross-sector) stakeholders, and able to present and explain analytical problems, approach, results and recommendations
    
  • Support in creating sprint planning by giving input and feedback
    
• Leveraging expert knowledge on machine data processing including source and scanner event mining, task processing, wafer processing etc. to support the PMA replacement in building trusted datasets for reporting and your data science prototypes.

Education and experience

Skills

• Affinity with data and business intelligence platforms, data analysis and analytics tools and techniques
  
• Ability to apply the latest analysis techniques
  
• Knowledge of statistics and experience using statistical packages for analyzing large datasets (Excel, SQL, R, Python, etc)
  
• Knowledge of data modelling, cleansing and transformation
  
• Knowledge/understanding of complex production (control) processes, preferably in a high tech, low volume environment.
  
• Ability to train and evaluate predictive and prescriptive models on metrics and to transfer this to industrialization requirements (e.g. model drift, active learning)
  
• Detailed knowledge of our machine data landscape, being able to process events towards actionable insights in a scalable way. Knowledge of operational process data (sequences), tasks, states, failure modes, EUV source is a pre.

• Strong capability for problem solving, thinks creative, out of the box
  
• Perseverance to ‘find the needle in the haystack’
  
• Able to work effective and constructive in multidisciplinary teams
  
• Professional communication: can explain and present technical matters within team
  
• Internal drive for efficiency and able to work disciplined and accurate
  
• Pragmatic, pro-active, ‘self-propelling’ way of working and able to operate in a dynamic environment
  
• Take responsibility: say what you do and do what you say
  
• Transparent and self-reflective: learn from your own mistakes
  
• Observe the wishes and needs of the customer, anticipate on them and then act accordingly.

• Hands-on experience with PowerBI, Python (including ML libraries and spark), Azure ML, Alteryx, Spotfire, R
  
• Experience with MLOps and Agile (SCRUM)
  
• Ability to deploy models (e.g. cloud deployment)
  
• Understanding of ASML business ecosystem
  
• Understanding of our operational databases (action planner, worklist manager, sequence runner)

Diversity & Inclusion

Other information