Applied Computer Vision and Image Processing for Semiconductor Wafer Metrology and Inspection system

Scanning Electron Microscope (SEM) are used widely in the semiconductor industry for metrology and inspection. Among the various types of SEMs, CD-SEMs are of profound importance mainly because they measure the CD (critical dimension) of the circuit patterns based on which the entire litho process is targeted. Review-SEMs and E-beam inspection tools are gaining importance as we shrink to N3 nodes and below because of their high resolution. However, as circuit patterns become smaller (pitches less than 32 nm) the extraction of repeatable and accurate defect locations along with CD metrology becomes significantly complicated especially post ADI (After Develop inspection). This is simply because at these pitches the number of pixels available to detect a defect or do metrology is approaching single digit numbers.

The goal of this research topic is to explore and apply advanced deep learning algorithms and architectures in computer vision domain for solving specific problems in E-Beam metrology and Inspection, more specifically for SEM image analysis.

The student will learn conventional process flow and work collaboratively toward 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 o address or overcome metrology/process control-based tool limitations.
5. Collaboration on patent/publications and presentations at international conferences/high-indexed journals
   
    
   
   Required Specialized skillset(s):
   
    

• 1. You work independently, have a strong feeling of responsibility, and be committed to timing and milestones set forward by different research projects/conferences.
• 2. 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. 
• 3. Strong Programming skills (Python, C, C++, skill etc.).
• 4. You must be visionary and with a multi-disciplinary attitude.
• 5. You have excellent analytical skills to interpret the obtained research results. 
• 6. You are a team player and have strong communication skills. 
• 7. Your English is fluent, both speaking and writing.

Type of work: 50% for preparation and execution of experiments, 30% for data analysis, 20% for literature study.

Type of project: Combination of internship and thesis, Thesis.

Duration: 6 months. Can be extended based on performance.

Required degree: Master of Engineering Technology, Master of Science, Master of Engineering Science

Required background: Computer Science/Engineering, Electrotechnics/Electrical Engineering, Physics, Machine Learning/Artificial Intelligence.

Supervising scientist(s): For further information or for application, please contact: Sandip Halder (Sandip.Halder@imec.be) and Bappaditya Dey (Bappaditya.Dey@imec.be)

Our group website: https://sites.google.com/view/imec-ap-ml/home

Imec allowance will be provided.