Master thesis: Active learning for deep-learning-based deviation classification in photomasks

2 days ago

Taby Sweden Mycronic Full time 60,000 - 120,000 per year
Description

About Mycronic

Mycronic is a global high-tech company whose innovative solutions have been advancing electronicstechnology for over 40 years. Our innovative solutions, including our market-leading mask writers, have madea significant impact on the electronics industry. Today we continue to grow and serve customers in anexpanding variety of industries. What we do impacts the future of technology, and in turn, the way we live ourlives tomorrow.

At this moment there is no other company in the world that can compete with Mycronic's mask writers. Alldisplays you see, whether it is your TV, laptop screen, smart watch, or infotainment screen in your car, aremanufactured with the use of Mycronic's machines. The same technology is also used in the semiconductorindustry. The process for the manufacturing happens at a nanometer level, smaller than blood cells andviruses. For all of this to be possible, a great emphasis is put on the quality of software and hardware.

Background

An important aspect in the manufacturing of lithographic masks at nanometer-scale precision is the ability to verify that the manufactured patterns match the expected performance. Much of this inspection and decision-making is today done manually, due to both the history of development in the semiconductor industry, and the ability and mandate of the machine operator to decide which deviations are to be considered as within or outside limits. In this aspect, machine learning offers a promising support functionality which can assist and speed up operator decisions and/or reduce the number of cases that need to be manually reviewed.

One of the challenges in training deep learning models for photomask deviation classification is the cost of data annotation, since the task is usually done by trained operators and data confidentiality often limits the use of crowdsourcing. Therefore, it is desirable to select the most informative samples for labeling to maximize the model performance with limited labeling resources.

Scope

The main goal of the thesis is to explore models and methods for human-in-the-loop active learning for training models for deviation classification in photomasks used in the semiconductor industry. The project scope can also be adapted based on individual interests and background.

Project outline:

  • Conduct literature review to set the direction and scope of the project.
  • Implement models and methods or extend existing implementations.
  • Plan experiments, train models, and evaluate performance.
  • Identify and suggest directions for future investigation.
  • Present the results in a technical report as well as in an oral presentation.

Details

Credits: 30 hp 

Thesis start: Early 2026

Location: In person or hybrid, at Mycronic's headquarters in Täby just outside of Stockholm

Qualifications

  • Master's degree students who are currently in the final year of their master's program.
  • The project requires knowledge in deep learning, and TensorFlow or PyTorch.
  • Previous experience with machine learning research or R&D is meritorious.

Apply for the position

Click 'Apply now' below and submit your CV, cover letter and academic transcripts.

Contact and further information

Stefan Fu, Machine Learning Engineer, PG Software Data Science,
 

  • Master thesis: Bridging Physics and Machine Learning through Explainable Image Generation

    2 days ago

    Taby, Sweden Mycronic Full time 540,000 - 840,000 per year

    DescriptionBridging Physics and Machine Learning through Explainable Image GenerationBackground and MotivationIn advanced industrial applications, physics-based simulation models are widely trusted for their interpretability and strong theoretical foundations. However, these models often struggle to describe the wide range of complex and nonlinear effects...

  • Master Thesis

    4 days ago

    Sweden Atlas Copco Full time 350,000 - 550,000 per year

    Your role Level of thesis project: Master thesisEducation requirement: Computer Science, Artificial Intelligence, Machine Learning, or a related fieldFunctional area: Atlas Copco Industrial Technique AB, Application SoftwareNumber of students for this project: 1Start: Flexible, early 2026 preferredWe are seeking a curious and highly driven Master student...

  • Master Thesis: Finite Element and Machine Learning for Dynamic Cable Sensors

    4 days ago

    Sweden NKT Full time 60,000 - 90,000 per year

    BackgroundMotivated by the urgent need to address climate change, the generation of renewable energy is on the rise. To reach out for new natural resources, such as wind, wind farms are now more often being installed offshore at sea, further off the coast. In such places, winds blow with much greater force and more frequently than on land. High voltage (HV)...

  • Machine Learning Engineer

    2 days ago

    Östra Hamngatan Göteborg, Sweden, Sweden Modulai Full time 80,000 - 120,000 per year

    MACHINE LEARNING ENGINEERAs a member of the ML-team you will be working with a broad range of problems with one common denominator – ML will be the key ingredient.You will have to analyze the problem at hand, come up with a solution strategy and execute it. This typically entails gaining an in-depth understanding of the challenge, understanding the...

  • Master's Thesis Work at Ovako

    4 days ago

    Stockholm, Ospecificerad arbetsort, Sweden Ovako Group Full time 40,000 - 80,000 per year

    Ovako Group Our employee journeyAt Ovako, we believe that work is more than just a job – it's an opportunity to be part of something meaningful. We foster an open and friendly atmosphere where everyone is valued, providing opportunities for personal and professional development. Many of us find fulfillment in knowing that our work contributes to...

  • Master Thesis Application for Spring 2026

    4 days ago

    Typsnittgatan Uppsala, Sweden Nodica Group AB Full time 40,000 - 80,000 per year

    Who We AreScandiNova develops high-technology pulse modulators used in medical technology, research, and industry – including applications such as cancer therapy, particle accelerators, and weather radar systems.Master's Thesis at ScandiNovaAt ScandiNova, we highly value thesis projects and the contributions of our students. We are therefore always eager...

  • Senior Machine Learning Engineer

    2 days ago

    Östra Hamngatan Göteborg, Sweden, Sweden Modulai Full time 120,000 - 240,000 per year

    SENIOR MACHINE LEARNING ENGINEER (SMLE) - SwedenAs a member of Modulai you will be working with a broad range of problems with one common denominator – ML will be the key ingredient. As a SMLE you will be responsible for team success and advisory to both teams and clients. In this role, you will be responsible for engaging clients and teams from the...

  • Master Thesis: AI-Driven Simulation of Non-Newtonian Polymer Flow in Cable Extrusion

    4 days ago

    Sweden NKT Full time 250,000 - 500,000 per year

    BackgroundAs offshore wind energy continues to grow, high-voltage (HV) cables are essential for transmitting power from sea to shore. The insulation quality of these cables is largely determined during the extrusion process, where molten polymer layers are applied. Traditional CFD methods can be computationally expensive and time-consuming, especially for...

  • Senior Project Manager

    2 days ago

    Sweden master-TMS Full time 120,000 - 180,000 per year

    In Sweden -StockholmWe are looking for a highly experienced andmotivated Expert Project Manager to lead one of our most strategic andhigh-priority initiatives: the global transformation from SAP ECC to SAPSuccessFactors. This role is pivotal to the success of our overalltransformation journey. The ideal candidate will possess deep expertise in SAPprogram...

  • Senior Machine Learning Engineer

    4 days ago

    Fredsborgsgatan , Stockholm, Sweden Soltia AB Full time 100,000 - 120,000 per year

    Company Description We are a consulting company with a bunch of tech-savvy and happy peopleWe love technology, we love design, and we love quality. Our diversity makes us unique and creates an inclusive and welcoming workplace where every individual is highly valued.With us, everyone can be themselves while respecting others for who they are. We believe that...