Semiconductor industry; we are looking for 6 PhDs

Introduction

Do you like applying mathematical theories in practice to solve real-world challenges? Do you like working with top-notch, internationally recognized industrial partners? Would you like to push the boundaries of system-level modelling, analysis, design, exploration and synthesis beyond the current state-of-the-art? Or are you curious to learn more about the application of AI for system diagnostics and system evolution? We are offering six PhDs positions across the department of Mechanical Engineering, Electrical Engineering and Mathematics and Computer Science that focus on solving cutting-edge design automation questions that will drive innovation in the Brainport region and beyond.

Job Description

The semiconductor industry is vital to global economic growth and technological progress, powering everything from energy solutions to healthcare innovations. Some parts of the design of these high-tech systems - lithography machines – can be automated. However, current design automation solutions are limited to specific domains or subsystems. Holistic system-level design is a necessary next-step because of the complexity of these systems. This implies going beyond current domain-specific solutions by combining mechanical, electrical, software, data science, and AI-expertise.

We are seeking highly-motivated candidates for the six PhD positions advertised here that address the challenge above by pushing the boundaries of 1) system-level co-design of architecture, functionality and performance, and 2) leverage system models to monitor and understand operational behaviour of systems and act upon irregularities. This description will continue with a description of all six positions:

PhD 1: System architecture exploration (supervision by: Theo Hofman and Pascal Etman) [Department of Mechanical Engineering]

The research by this position aims to achieve automated computational design synthesis of system topologies. This will result in new and novel system topologies which can be automatically analysed and evaluated based on construction and performance indicators. This will require an insight into how to fully automate the discrete topology design synthesis process across system levels and how to learn component descriptions and how these can be interconnected.

PhD 2: Scenario-based compositional system-level performance engineering (supervision by: Twan Basten, Marc Geilen) [Department of Electrical Engineering]

The research planned for this position will explore how to achieve correct behavior and required performance (in terms of throughput, latency), while considering concerns and constraints from various engineering domains by leveraging scenario-based design. This methodology considers systems from a behavioral perspective, clustering behaviors with similar characteristics. The envisioned model-based performance engineering starts from use cases (typical and exceptional) and various system scenarios (different operating modes, failures). This will require the development of suitable domain-specific languages (DSLs) to specify use cases from the perspective of the relevant domains as well as model transformation, analysis, and synthesis algorithms that provide functionally correct system configurations with a guaranteed performance. The research focuses on suitable domain models and the required model transformation, analysis, and synthesis approaches.

We require candidates for PhD 2 to have good software engineering and programming skills, good knowledge on modeling cyber-physical systems, and preferably experience with DSL development.

PhD 3: Timing-aware distributed supervisory controller synthesis (supervision by: Michel Reniers and Martijn Goorden) [Department of Mechanical Engineering]

The automatic synthesis of supervisory controllers will support the design process of lithography machines. To achieve a computationally tractable automatic synthesis, a deep understanding is required into how the (control) architecture of lithography machines and the types of models can be used to capture their behaviour and requirements. This will enable splitting the problem of synthesizing safe supervisors into smaller synthesis problems, the results of which can be composed into a solution for the original system. This will require an understanding of how existing system decompositions and interface specifications be translated into models suitable for hierarchical/distributed supervisory control synthesis.

We require candidates for PhD 3 to have knowledge of discrete-event systems, and knowledge of or interest in learning about formal methods, in particular, the theory of Supervisory Controller Synthesis.

PhD 4: AI-driven legacy system explanation and refactoring (supervision by: Lina Ochoa Venegas, Michel Chaudron, Jacob Krüger - collaboration with: Stef van den Elzen) [Department of Mathematics and Computer Science]

Maintaining an understanding of complex systems with a vast amount of software requires effective architecture explanation frameworks, visualizations and identification of architectural refactoring opportunities in legacy systems. These elements will support onboarding, enhance team efficiency, reduce reliance on system experts, and accelerate software maintenance and development. This will require an understanding of how a system architecture can be  extracted and represented in a language-agnostic way, relying in the capabilities of program analysis,generative AI, and advanced visualisation techniques.

We require candidates for PhD 4 to hold both a bachelor’s and a master’s degree in Computer Science, Data Science, Software Engineering, or a closely related field. Prior experience with the application and understanding of generative AI methods and tools, as well as a solid background in software engineering and a strong interest on visualisation techniques, are highly desirable.

PhD 5: Data mining for diagnostics (supervision by: Mykola Pechenizkiy, Songgaojun (Amy) Deng) [Department of Mathematics and Computer Science]

This research, in close collaboration with ASML AI Research, is based on the promise of a novel framework that integrates evolving knowledge graphs (KGs) with domain-specific foundation models to enhance diagnostic capabilities. This research will look into how knowledge graphs be designed and generated from a combination of software stack, legacy code, and documentation (V-model steps: requirements, system design, module design, etc) to capture equipment behavior, process steps, and causal failure relations, as well as discrepancies between expected behavior from requirements and actual failures from deployed system. The latter knowledge graphs will then be integrated with foundation models to enhance machine interpretability in complex diagnostic environments.

PhD 6: Automating health monitoring in semicon equipment (supervision by: Nathan van de Wouw, Tom Oomen, Michelle Chong) [Department of Mechanical Engineering]

This project aims to devise innovative monitoring technology for high-tech systems to perform (semi) autonomous fault isolation, and predictive monitoring. For high-tech equipment, such as those used in the production of semiconductors, monitoring is a challenge because of the highly complex interconnected systems they are consisting of many components/modules, which are functionally, digitally, and physically connected. To achieve such monitoring technology, an understanding is required of how to support the identification and prediction of rare failures, for which only scarce datasets are available.

Current health monitoring technology is typically designed for either (i) individual system components/modules (which would require removing the component from the system, which is not possible in practice), or (ii) for the system as a whole. The first approach fails to account for the interaction between modules and its effect on the whole system. The second approach makes it challenging to isolate which module may be failing and how to zoom in on the part of the system that is the root cause of the failure. This PhD position will address this challenge by developing hierarchical diagnostic tools for complex dynamical systems.

We require candidates for PhD 6 to have a strong background in mathematical control theory and a keen interest in hybrid dynamical systems, observer design, learning techniques and optimization.

Job Requirements

• A master’s degree (or an equivalent university degree) in systems and control, mechanical engineering, electrical engineering, mathematics and/or computer science, data science, or applied mathematics. (depending on the position applied for)
• Strong analytical and problem-solving skills, with a passion for tackling complex, multi-disciplinary challenges.
• Eager to work within an interdisciplinary team of industry and academic researchers.
• Excellent communication and collaboration skills to work effectively within a large project team. 

Conditions of Employment

A meaningful job in a dynamic and ambitious university, in an interdisciplinary setting and within an international network. You will work on a beautiful, green campus within walking distance of the central train station.

A challenging and rewarding PhD position in a vibrant research environment at the forefront of semiconductor technology. The opportunity to work on a high-impact project with strong industry and academic partners. A comprehensive training program to enhance your research and professional skills. In addition, we offer you: 

• Full-time employment for four years, with an intermediate assessment after nine months. You will spend a minimum of 10% of your four-year employment on teaching tasks, with a maximum of 15% per year of your employment. 
• Salary and benefits (such as a pension scheme, paid pregnancy and maternity leave, partially paid parental leave) in accordance with the Collective Labour Agreement for Dutch Universities, scale P (min. € 3,059 - max. € 3,881).  
• A year-end bonus of 8.3% and annual vacation pay of 8%. 
• High-quality training programs and other support to grow into a self-aware, autonomous scientific researcher. At TU/e we challenge you to take charge of your own learning process. 
• An excellent technical infrastructure, on-campus children's day care and sports facilities.  
• An allowance for commuting, working from home and internet costs. 
• A Staff Immigration Team and a tax compensation scheme (the 30% facility) for international candidates. 

Information

Do you recognize yourself in this profile and would you like to know more? Please contact 
the supervisors as indicated in the PhD position using the contact details below:

PhD1: prof.dr.ir Theo Hofman, t.hofman@tue.nl
PhD2: prof.dr.ir. Twan Basten, a.a.basten@tue.nl
PhD3: prof.dr.ir. M.A. Reniers, m.a.reniers@tue.nl
PhD4: Dr. Lina Ochoa Venegas, l.m.ochoa.venegas@tue.nl
PhD5: Prof.dr. Mykola Pechenizkiy, m.pechenizkiy@tue.nl
PhD6: Prof.dr.ir. Nathan van de Wouw, N.v.d.Wouw@tue.nl

Visit our website for more information about the application process or the conditions of employment. You can also contact HR Services Gemini (HRServices.Gemini@tue.nl) or HR Advice (HRAdviceME@tue.nl).

Curious to hear more about what it’s like as a PhD candidate at TU/e? Please view the video.

Are you inspired and would like to know more about working at TU/e? Please visit our career page.

Application

We invite you to submit a complete application by using the apply button. The application should include a:

• Cover letter in which you describe your motivation and qualifications for the position.
• Curriculum vitae, including a list of your publications and the contact information of three references. 
• If you are interested in applying for multiple positions, clearly indicate in your cover letter the order of preference and why you have chosen this specific order.

We look forward to your application and will screen it as soon as we have received it. Screening will continue until the positions have been filled.

Please note

• You can apply online. We will not process applications sent by email and/or post. 
• A pre-employment screening (e.g. knowledge security check) can be part of the selection procedure. For more information on the knowledge security check, please consult Chapter 8 of the National Knowledge Security Guidelines.
• Please do not contact us for unsolicited services.