At a glance

Location: Fab 10N/X, Singapore
Work type: Onsite

What they are looking for

PythonMachine learningData analysisStatistical process controlGenerative ai

Location: Fab 10N/X, Singapore

Our vision is to transform how the world uses information to enrich life for all.

Join an inclusive team passionate about one thing: using their expertise in the relentless pursuit of innovation for customers and partners. The solutions we build help make everything from virtual reality experiences to breakthroughs in neural networks possible. We do it all while committing to integrity, sustainability, and giving back to our communities. Because doing so can fuel the very innovation we are pursuing.

Location

Singapore

Department

Process and Equipment Engineering, Chemical Vapor Deposition (CVD)

Project Title

Workstation Performance Acceleration Through an Artificial Intelligence-Driven Root Cause Analysis Tool

Project Description

The intern will explore the application of Artificial Intelligence and machine learning to incident analysis within the Chemical Vapor Deposition process area. The project aims to transform equipment, process, and human-written incident data into structured, actionable insights that enable engineering teams to investigate recurring workstation failures more effectively.

Through this project, the intern will gain exposure to semiconductor process and equipment engineering while developing and validating an AI-Enabled root cause analysis solution. The experience will involve technical learning, data analysis, model experimentation, and cross-functional engagement with production, equipment, process, hardware, and planning subject-matter experts.

Objective of the Project

Develop an AI-Enabled approach for interpreting human-written incident records from the Equipment Tracking Interface (ETI).

Organize incident data into meaningful Pareto categories to provide clearer investigation direction.

Explore correlations across equipment alarms, Fault Detection and Classification data, Statistical Process Control data, and historical incident records.

Strengthen incident validation through appropriate integration with Microsoft Teams.

Identify recurring failure patterns and opportunities to accelerate engineering learning cycles.

Opportunities for Full-Time Employment

High-performing interns may be considered for suitable full-time or future internship opportunities, subject to business needs, position availability, and the applicable selection process.

Project Scope

Prepare, classify, and analyze incident inputs from equipment alarms, Fault Detection and Classification systems, Statistical Process Control records, and the Equipment Tracking Interface.

Explore and train Artificial Intelligence or machine learning models to interpret technical context and human-written terminology in incident logs.

Develop methods for grouping incidents into Pareto categories and identifying chronic or recurring failure signatures.

Evaluate an integration concept between the Equipment Tracking Interface and Microsoft Teams for incident validation.

Conduct correlation studies and model validation using historical manufacturing data under the guidance of engineering subject-matter experts.

Learning Opportunities

Gain practical exposure to Chemical Vapor Deposition processes, semiconductor equipment engineering, process control, and workstation performance.

Learn how Artificial Intelligence, machine learning, and Large Language Model techniques can be applied to unstructured engineering records.

Apply root cause analysis methods such as Failure Mode and Effects Analysis, Eight Disciplines problem-solving, Pareto analysis, and Statistical Process Control.

Build experience in data preparation, model simulation, validation, visualization, and the communication of technical findings.

Engage with cross-functional experts from process, equipment, production, hardware, and planning functions.

Deliverables

A validated AI model or prototype capable of interpreting human-written Equipment Tracking Interface incident logs.

A methodology for categorizing incidents into Pareto groups and identifying recurring failure patterns.

A proof of concept for linking relevant incident records with Microsoft Teams validation inputs.

Data visualizations, correlation-study results, and documented recommendations for further solution development.

Impact of the Project

Target a productivity improvement of approximately 12 engineering hours per week.

Reduce information gaps in incident validation by connecting relevant data and engineering inputs.

Accelerate learning cycles for chronic issues by an estimated two to three weeks.

Improve the consistency and clarity of root cause investigation directions for engineering teams.

Skillsets Required

Strong analytical, logical, and critical-thinking skills with an interest in semiconductor manufacturing and engineering problem-solving.

Knowledge of statistical data analysis, Design of Experiments, Statistical Process Control, or root cause analysis methods is advantageous.

Familiarity with Python, structured data analysis, machine learning, Generative AI, Large Language Models, or other AI-Enabled workflows is preferred.

Ability to apply digital fluency and role-appropriate AI literacy responsibly while exercising sound judgment and complying with organizational, confidentiality, and legal requirements.

Effective communication and collaboration skills for engagement with cross-functional engineering teams.

Course of Interest

The ideal candidate should be pursuing a bachelor’s or advanced degree, or an equivalent qualification, in Chemical Engineering, Electrical and Electronic Engineering, Mechanical Engineering, Materials Science and Engineering, Computer Engineering, Computer Science, Data Science, Applied Mathematics, Physics, or a related field.