Master thesis-Tracking defect evolution to predict yield in semicon CMOS via machine learning

Completed Bachelor's degree in data science or comparable

• Experience in Machine Learning and/or Artificial Intelligence
• Experience in semiconductor environment beneficial
• Independent and structured way of working

We offer competitive salaries and additional benefits based on your performance, experience, and qualifications. Employment is in accordance with the collective agreement for the electrical and electronics industry, employment group E (https://www.feei.at/aktuelles/mindestloehne-und-gehaelter-eei/).

The ams OSRAM Group is a global leader in innovative light and sensor solutions. With more than 110 years of industry experience, we combine engineering excellence and global manufacturing with a passion for cutting-edge innovation enabling transformative advancements in the automotive, industrial, medical, and consumer industries. "Sense the power of light" - our success is based on the deep understanding of the potential of light and distinct portfolio of emitter and sensor technologies. Around 19,700 employees worldwide drive innovations alongside societal megatrends. Find out more about us on https://ams-osram.com The CSA division supplies sensors that bridge the gap between the world we live in and the digital world of machines. By converting physical signals - heartbeats, sounds, light waves - into data, we enable robots, cars and other devices to interact with people and improve our world. What drives CSA is a relentless desire to contribute to technology and have a meaningful impact on the world. This business thrives on solving complex problems and partnering with global leaders at the forefront of technological advancement. Our goal: to push the boundaries of sensor technology and empower innovators to make the world smarter, healthier and happier. Your new responsibilities Theoretical Part: * Get an understanding of what defect data is and how it can be handled. * Comprehensive literature review of state of the art usage of defect data within semiconductor industry (yield prediction, signature prediction, defect classification etc.). * Literature review of possibly already existing models incorporating defect data. * Evaluation of approaches to establish yield predictions with defect data Practical Part: * Close cooperation with various departments (Defect, IT, Product Engineering etc.) * Understand defect classification/categorization * Get actual state of available data and its usage * Define possible solutions for the problem statement