Location
Singapore
Department
Process Development Engineering
Project Title
AI-Enabled Process Analytics for Thin-Film Deposition and Ion Implant Technology Development
Project Description
This internship project provides an opportunity to develop and apply Artificial Intelligence (AI), machine learning, data analytics, and statistical modelling methodologies within advanced semiconductor technology development.
The intern will participate in a structured learning project focused on extracting insights from process, metrology, inline, and electrical datasets generated during thin-film deposition and ion implantation technology development activities. Through collaboration with engineering mentors, the intern will explore AI-Enabled approaches to process characterization, variability analysis, and predictive modelling for advanced semiconductor manufacturing processes.
The project emphasizes the development of technical competencies in semiconductor process technology, data science, statistical learning, and Generative AI-assisted analytical workflows while contributing recommendations that may enhance process understanding and technology development effectiveness.
Objective of the Project
The objective of this project is to evaluate how Artificial Intelligence, machine learning, and statistical analytics can be applied to semiconductor technology development data to:
- Identify process trends, correlations, and sensitivities.
- Develop predictive models for process and material characteristics.
- Explore methodologies for variability monitoring and anomaly detection.
- Generate data-driven insights that improve process learning and decision-making.
- Enhance understanding of AI-Enabled workflows within semiconductor process development.
Opportunities for Full Time Employment
High-performing interns may be considered for future internship, graduate, or full-time employment opportunities, subject to business requirements, individual performance, and available openings.
Project Scope
The intern will work on a structured project that may include:
AI & Data Analytics
- Conduct exploratory data analysis on process, metrology, inline, and electrical datasets.
- Develop and evaluate machine learning models, including regression, classification, clustering, and time-series techniques.
- Create physics-informed features relevant to semiconductor processes such as deposition and ion implantation technologies.
- Investigate AI-Enabled approaches for predictive process learning and optimization.
Statistical Analysis
- Apply statistical methods including regression analysis, hypothesis testing, multivariate analysis, and design-of-experiment (DOE) interpretation.
- Evaluate anomaly detection and drift monitoring methodologies for process data.
- Analyze technology development datasets to identify learning opportunities and potential process improvement areas.
Data Engineering & Visualization
- Develop reusable data preparation and feature engineering workflows.
- Create dashboards, visualizations, and technical summaries to communicate findings.
- Explore AI Assistant or Generative AI tools to improve analysis efficiency and technical communication.
Technical Collaboration
- Participate in technical discussions with process development, equipment, integration, and data analytics teams.
- Present project findings, technical observations, and recommendations throughout the internship.
Learning Opportunities
Through this internship, the candidate will gain exposure to:
- Advanced semiconductor process development methodologies.
- Thin-film deposition technologies, including Chemical Vapor Deposition (CVD), Atomic Layer Deposition (ALD), and Physical Vapor Deposition (PVD).
- Ion implantation process fundamentals.
- Semiconductor metrology and characterization techniques.
- Machine learning and Artificial Intelligence applications in manufacturing environments.
- Statistical modelling and data-driven decision-making.
- Generative AI and AI-Enabled analytical workflows.
- Technical presentation and stakeholder communication skills.
Deliverables
The intern is expected to complete a project package that may include:
- Data analysis notebooks and documented workflows.
- Machine learning model development and evaluation results.
- Visualization dashboards and technical summaries.
- Final presentation outlining methodology, key findings, and recommendations.
- Documentation describing project outcomes, learning observations, and future opportunities for investigation.
Impact of the Project
This project may contribute to:
- Improved understanding of semiconductor technology development data.
- Enhanced visibility into process variability and performance relationships.
- Evaluation of AI-Enabled methods for process learning and predictive analytics.
- Development of scalable analytical approaches that support future technology development initiatives.
- Advancement of digital transformation and data-driven engineering practices.
Skillsets Required
Required
- Proficiency in Python programming for data analysis and machine learning.
- Knowledge of statistical analysis and data science fundamentals.
- Familiarity with data manipulation libraries such as NumPy, Pandas, SciPy, or equivalent.
- Analytical problem-solving skills and ability to interpret technical datasets.
- Effective written and verbal communication skills.
- Basic AI proficiency, including familiarity with AI-Enabled tools, Generative AI platforms, AI Assistants, Large Language Models (LLMs), or Agentic AI concepts.
Preferred
- Knowledge of semiconductor manufacturing or device fabrication.
- Exposure to thin-film deposition, ion implantation, metrology, or process engineering concepts.
- Familiarity with machine learning techniques and model development.
- Experience with data visualization platforms such as Tableau, Power BI, Streamlit, or equivalent tools.
- Understanding of Design of Experiments (DOE), Statistical Process Control (SPC), or manufacturing analytics.
- Exposure to cloud computing or big-data platforms such as Azure, AWS, GCP, or Spark.
Course of Interest
The ideal candidate should be pursuing a Bachelor's, Master's, or PhD degree in Materials Science and Engineering, Electrical Engineering, Chemical Engineering, Physics, Data Science, Computer Science, Statistics, Applied Mathematics, Artificial Intelligence, or a related discipline.
Duration of Period
The ideal candidate should be able to commit to a full-time internship period of 6 months.
