About this role
Data Science | AI Internship: Reinforcement Learning Beschrijving Introduction The Applied Data Science Technical Competence team at ASML develops data-driven solutions that improve machine performance through machine learning and artificial intelligence. Working closely with domain experts, the team transforms complex data into practical solutions that support diagnostics, maintenance, calibration, and control. In this internshipyou will help improve how AI systems learn from engineer interactions during diagnostic activities. Your work will contribute to creating adaptive AI solutions that continuously improve based on human feedback. This internship offers the opportunity to work on a highly relevant challenge within the field of AI and human-in-the-loop learning. Your assignment During this internship, you will design and evaluate a Reinforcement Learning with Human Feedback (RLHF) framework that enables AI systems to learn from interactions with field engineers. The goal is to improve diagnostic recommendations by systematically capturing feedback and converting it into actionable learning signals. You will combine reinforcement learning, natural language processing, and human-in-the-loop AI methods to investigate continuous improvement mechanisms. Your main responsibilities will be: - Design a framework to capture engineer-AI interaction signals during diagnostics. - Analyze how user actions can be translated into meaningful feedback signals. - Develop reward models for reinforcement learning using human feedback. - Build and evaluate prototype solutions using Python and deep learning frameworks. - Investigate methods to improve diagnostic recommendation quality over time. - Assess the effectiveness and robustness of the proposed RLHF approach. - Present findings and recommendations to stakeholders within the team. This is a master thesis internship for minimum 5 months, minimum 4 days per week (3 days on-site). The st...