Foundation Models, World Models and Continual Learning for Semiconductor Lithography and Metrology: Advancing Machine Learning towards High-NA EUV Process Control

What will you do? As patterning moves to high-NA EUV lithography, process windows shrink. Thinner resists produce noisier, lower-contrast SEM images, and stochastic failures (missing contacts, micro-bridges, line breaks) become a dominant yield limiter. Today, computational lithography (OPC, process simulation), metrology and defect inspection are handled as separate problems. Each relies on its own task-specific models, large amounts of labelled data and frequent recalibration. None of them builds a shared, transferable understanding of how design intent, process conditions and measured outcomes relate to each other. Recent advances in machine learning offer a way to change this. Transformer-based foundation models, Joint-Embedding Predictive Architectures (I-JEPA, V-JEPA), latent world models and continual learning methods can learn from large amounts of unlabelled data, predict outcomes under changing conditions, and adapt to new tasks without retraining from scratch. Semiconductor manufacturing is a demanding testbed for these methods. Its data are noisy, scarce in labels, multi-modal and governed by physics that is only partially known, and it requires nanometre-level accuracy. This Master’s internship advances these methods in that setting. The semiconductor process flow sets the boundary conditions and evaluation criteria. Depending on the candidate’s profile, the thesis will focus on one or more of the following research directions: • Self-supervised foundation models for metrology images: pretraining transformer and JEPA-style encoders on large unlabelled SEM/TEM datasets, and studying representations that hold up under low dose, low contrast and anisotropic noise. • World models of the patterning process: learning action-conditioned latent models that predict the measured outcome from design (layout/GDS) and process conditions (dose, focus, illumination, mask bias). This enables counterfactual “what-if” analysis across the process window. • Label-free and few-shot defect detection: detecting rare, novel and stochastic defects through prediction error, density modelling or few-shot learning, with calibrated uncertainty. • Continual learning across layers, tools and nodes: adapting models to new data distributions without catastrophic forgetting, and quantifying how many labelled samples each new task requires. • Machine learning for computational lithography: fast learned surrogates for lithography simulation, ML-assisted OPC/inverse lithography, and learned mask/process correction, benchmarked against conventional rigorous methods. • Multi-modal, uncertainty-aware learning: combining metrology images, layout and tool/process data into representations that support reliable process control decisions. By tackling these challenges, the project aims to advance the state of the art in representation learning, predictive modelling and adaptation under strict noise, data and accuracy constraints. The findings should apply beyond semiconductor manufacturing to other scientific and industrial imaging domains. The selected intern/student will learn the conventional patterning process flow. They will work collaboratively on developing and applying machine-learning-based algorithms with four goals: 1) reducing computational cost compared to rigorous simulation, 2) reducing tool cycle time and metrology sampling, 3) enabling a predictive process control approach for advanced-node manufacturing, and 4) improving the quality and information content of metrology data. Machine learning applicability includes: 1. Technical diligence: scope the research question, model choice, compute budget and evaluation protocol to meet the target performance and timeline. 2. Data curation and analysis: collect and analyse image data (SEM/TEM/EDR/…), layout clips and process/tool data. Formulate hypotheses in a feedback loop with domain experts. 3. Model development: build new architectures or substantially improve existing ones (transformers, JEPA, world models, continual learning, generative models) for the chosen task, with a focus on methodological contribution. 4. Rigorous evaluation: benchmark against strong baselines, with ablations, uncertainty quantification and analysis of generalization across data distributions. 5. Dissemination: collaborate on publications targeting top-tier machine learning and computer vision venues (CORE A*/A), such as NeurIPS, ICML, ICLR, CVPR, ICCV and ECCV, and high-impact journals such as IEEE TPAMI, IJCV and TMLR. 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 be supervised towards publishing at top-tier ML/CV venues, with access to real, non-public industrial metrology data rarely available to academic researchers. You will join a young and enthusiastic team of researchers and domain experts in machine learning, lithography and metrology. The Master’s internship position is available immediately. Who are you? ✓ You hold at least a Bachelor’s degree or are currently pursuing a Master’s degree at a reputable university in Computer Science, Computer Engineering, or Physics with a strong specialisation in advanced machine learning. Coursework in deep learning, computer vision or self-supervised learning is a plus. ✓ You can work independently, demonstrate a strong sense of responsibility, and keep to the timelines and milestones defined by ongoing research projects and conference deadlines. You are genuinely motivated by the research topic and committed to completing a research thesis as part of your university degree programme. ✓ You have a strong research interest in modern deep learning, such as transformers, self-supervised learning, world models, continual learning or generative models, and you are eager to advance the state of the art. Hands-on experience with PyTorch (or JAX) is expected. Experience training large models on GPU clusters is a strong plus. ✓ You have strong programming skills in Python. C/C++ is a plus. ✓ You are motivated to publish at top-tier machine learning and computer vision conferences. Prior publications at such venues are a strong plus. ✓ You are curious about the physical problem behind the data. No prior knowledge of lithography, microscopy or semiconductor processing is required, and the necessary domain background will be provided during the internship. ✓ You have excellent analytical skills for interpreting research results, including negative ones. ✓ You are a team player with strong communication skills. ✓ Your English is fluent, both spoken and written. Interested? Send your application, or any questions about this internship, by email to Bappaditya Dey (bappaditya.dey@imec.be). Use this subject line: “MS Thesis Application: Foundation Models, World Models and Continual Learning for Semiconductor Lithography and Metrology”. Applications should include: (a) SoP (clearly describing your research background and interests, any specific research skills, and which research direction(s) above interest you most; Physics applicants should describe their machine learning coursework and projects) (b) your professional résumé [max. 2 pages] (c) your latest degree transcript (d) GRE/TOEFL score [preferable but not mandatory] (e) previous publication record and/or links to code repositories (if any) Our research group website: https://sites.google.com/view/imec-ap-ml/home Type of internship : PhD internship, Master internship, Bachelor internship Duration : 6 months, can be extended to 9 months. Required educational background : Computer Science, Physics Supervising scientist(s) : For further information or for application, please contact Bappaditya Dey ( Bappaditya.Dey@imec.be ) The reference code for this position is 2026-INT-316 . Mention this reference code in your application. Imec allowance will be provided for students studying at a non-Belgian university. Applications should include the following information: resume motivation current study Incomplete applications will not be considered