Computer Vision for Defect Inspection and Metrology: Solving Semiconductor Manufacturing Challenges towards Advanced Process Control using Machine Learning

Imec; Vlaams-Brabant; On-site; EUR 13,000 - 20,000; Full time

Benefits offered by this job

Fully funded internship scholarship

Opportunities for publications

Mentorship from imec team

Job summary

imec in Leuven offers a Master/PhD/Bachelor internship focusing on computer vision for defect inspection and metrology in advanced semiconductor manufacturing. You will collaborate with researchers to implement ML-based optimization, integrate metrology data with tool logs, and contribute to process control improvements.

The role emphasizes unsupervised/few-shot learning, uncertainty-aware models, and scalable algorithms, with mentorship and opportunities for publications.

Qualifications

• Candidates should be enrolled in or have completed a Bachelor/Master in Engineering/Computer Science.
• Strong foundation in ML/CV and data analysis.
• Fluent in English and able to communicate in a research team.

Responsibilities

• Assist in developing ML/CV models for defect inspection and metrology.
• Analyze tool logs and process data to improve defect localization.
• Collaborate on publications and conference presentations.
• Contribute to reducing computational cost and cycle time in semiconductor workflows.

Skills

Machine Learning

Computer Vision

Python

TensorFlow

PyTorch

Data Analysis

English Fluent

Education

Bachelor/Master in Engineering/CS

Tools

MATLAB

NumPy

Pandas

Job description

/ Computer Vision for Defect Inspection and Metrology: Solving Semiconductor Manufacturing Challenges towards Advanced Process Control using Machine Learning

Computer Vision for Defect Inspection and Metrology: Solving Semiconductor Manufacturing Challenges towards Advanced Process Control using Machine Learning

Master internship, PhD internship, Bachelor internship - Leuven | About a week ago

Redefining nanoscale defect intelligence for the high-NA EUV era

As semiconductor devices continue to scale with the adoption of high-NA (Numerical Aperture) Extreme Ultraviolet (EUV) lithography, defect inspection and metrology face unprecedented challenges. Identifying and measuring nanoscale defects requires methods that are both highly accurate and computationally efficient, yet existing inspection pipelines struggle to handle the massive, heterogeneous, and often imbalanced datasets produced in advanced manufacturing. Manual inspection and correlation of such data sources are infeasible, motivating the need for new computer vision and machine learning techniques.

This Master’s internship project addresses fundamental computer vision challenges arising from this domain, with the semiconductor process flow providing the boundary conditions and practical constraints. The scientific focus includes:

• Unsupervised and few-shot learning for defect detection, enabling robust identification of rare or novel defect types with minimal (labelled) data.
• Multi-modal and context-aware representation learning, integrating metrology images with tool logs and process data to improve defect localization and classification.
• Uncertainty-aware models that quantify confidence in inspection results, supporting reliable process control.
• Scalable and efficient vision algorithms that balance high accuracy with reduced computational and cycle-time costs.

By tackling these challenges, the project aims to advance the state-of-the-art in computer vision for high-precision defect inspection and metrology, with contributions that generalize beyond semiconductor manufacturing to other domains where anomaly detection under strict constraints is critical.

The selected intern/student will learn conventional process flow and will be responsible to work collaboratively towards developing and applying “Machine learning" based optimization algorithms with a goal to tackle the aforementioned challenges in terms of 1) Reducing computational cost, 2) reduce tool cycle time, 3) predictive process control approach in enabling advanced node semiconductor manufacturing. 4) Improving metrology data.

Machine learning applicability includes:

1. Brainstorm “Technical diligence” of the project: to meet desired performance and engineering timeline.

2. Tool Data Analysis: Collect data, analyse data, and suggest hypothesis with expertise feedback loop.

3. Image Processing applicability: Collect Image data (SEM/TEM/EDR/..), suggest ML based hypothesis to extract improved SEM based measurements.

4. Machine Learning Modelling – build from scratch or improving an existing algorithm for a given application task optimization and address or overcome metrology/process control-based tool limitations

5. Collaboration on patent/publications and presentations at international conferences/high-indexed journals.

What we do for you??

We offer a fully funded internship scholarship (subject to conditions) for a maximum duration of 9 months, contingent on satisfactory progress. The internship focuses on fundamental and innovative research with clear practical applications. You will join a young and enthusiastic team of researchers and domain experts. The Master’s internship position is available immediately.

Who you are?

• You hold at least a Bachelor’s degree or are currently pursuing a Master’s degree at a reputable university in Engineering/Science, preferably in one of the following fields:
• restricted
• Computer Science/Engineering, Electrotechnics/Electrical Engineering, Physics, Artificial Intelligence and Machine Learning (or any interdisciplinary course). Additional coursework in Machine Learning is a plus.
• You are able to work independently, demonstrate a strong sense of responsibility, and adhere to timelines and milestones defined by ongoing research projects and conferences. You should be genuinely motivated by the research topic and committed to completing a research thesis as part of your university degree program.
• You have a strong research interest in investigating different advanced machine learning architectures and algorithms appropriate in the context of specified problem domain as well as eagerness to advance the state-of-the-art. Knowledge of diverse framework [Tensorflow/PyTorch etc.] is a plus.
• You must be visionary and with a multi-disciplinary attitude.
• You have excellent analytical skills to interpret the obtained research results.
• You are a team player and have strong communication skills.
• Your English is fluent, both speaking and writing.

What will you do? As semiconductor devices continue to scale with the adoption of high-NA (Numerical Aperture) Extreme Ultraviolet (EUV) lithography, defect inspection and metrology face unprecedented challenges. Identifying and measuring nanoscale defects requires methods that are both highly accurate and computationally efficient, yet existing inspection pipelines struggle to handle the massive, heterogeneous, and often imbalanced datasets produced in advanced manufacturing. Manual inspection and correlation of such data sources are infeasible, motivating the need for new computer vision and machine learning techniques.

This Master’s internship project addresses fundamental computer vision challenges arising from this domain, with the semiconductor process flow providing the boundary conditions and practical constraints. The scientific focus includes:

• Unsupervised and few-shot learning for defect detection, enabling robust identification of rare or novel defect types with minimal (labelled) data.
• Multi-modal and context-aware representation learning, integrating metrology images with tool logs and process data to improve defect localization and classification.
• Uncertainty-aware models that quantify confidence in inspection results, supporting reliable process control.
• Scalable and efficient vision algorithms that balance high accuracy with reduced computational and cycle-time costs.

By tackling these challenges, the project aims to advance the state-of-the‑art in computer vision for high‑precision defect inspection and metrology, with contributions that generalise beyond semiconductor manufacturing to other domains where anomaly detection under strict constraints is critical.

The selected intern/student will learn conventional process flow and will be responsible to work collaboratively towards developing and applying “Machine learning" based optimisation algorithms with a goal to tackle the aforementioned challenges in terms of 1) Reducing computational cost, 2) reduce tool cycle time, 3) predictive process control approach in enabling advanced node semiconductor manufacturing. 4) Improving metrology data.

Machine learning applicability includes:

1. Brainstorm “Technical diligence” of the project: to meet desired performance and engineering timeline.

2. Tool Data Analysis: Collect data, analyse data, and suggest hypothesis with expertise feedback loop.

3. Image Processing applicability: Collect Image data (SEM/TEM/EDR/..), suggest ML based hypothesis to extract improved SEM based measurements.

4. Machine Learning Modelling – build from scratch or improving an existing algorithm for a given application task optimisation and address or overcome metrology/process control‑based tool limitations.

5. Collaboration on patent/publications and presentations at international conferences/high‑indexed journals.

What we do for you??

We offer a fully funded internship scholarship (subject to conditions) for a maximum duration of 9 months, contingent on satisfactory progress. The internship focuses on fundamental and innovative research with clear practical applications. You will join a young and enthusiastic team of researchers and domain experts. The Master’s internship position is available immediately.

Who you are?

• You hold at least a Bachelor’s degree or are currently pursuing a Master’s degree at a reputable university in Engineering/Science, preferably in one of the following fields:
• restricted
• Computer Science/Engineering, Electrotechnics/Electrical Engineering, Physics, Artificial Intelligence and Machine Learning (or any interdisciplinary course). Additional coursework in Machine Learning is a plus.
• You are able to work independently, demonstrate a strong sense of responsibility, and adhere to timelines and milestones defined by ongoing research projects and conferences. You should be genuinely motivated by the research topic and committed to completing a research thesis as part of your university degree program.
• You have a strong research interest in investigating different advanced machine learning architectures and algorithms appropriate in the context of specified problem domain as well as eagerness to advance the state‑of‑the‑art. Knowledge of diverse framework [Tensorflow/PyTorch etc.] is a plus.
• You must be visionary and with a multi‑disciplinary attitude.
• You have excellent analytical skills to interpret the obtained research results.
• You are a team player and have strong communication skills.
• Your English is fluent, both speaking and writing.

Type of internship: Master internship, PhD internship, Bachelor internship

Duration: 6 months. Can be Extended

Required educational background: Computer Science, Physics, Electrotechnics/Electrical Engineering

Supervising scientist(s): For further information or for application, please contact Bappaditya Dey ( [e-mail] )

The reference code for this position is 2026-INT-158. Mention this reference code in your application.

Only for self‑supporting students.

imec's cleanroom