University of Luxembourg
2 weeks ago
Postdoc in Machine Learning and Surrogate Modelling University of Luxembourg in Luxembourg
Degree Level
Postdoc
Field of study
Computer Science
Funding
Available
Country
Luxembourg
University
University of Luxembourg

How do Indian students apply for this?
Sign in for free to reveal details, requirements, and source links.
Where to contact
Keywords
About this position
The University of Luxembourg, a leading international research university, offers a postdoctoral position in Machine Learning and Surrogate Modelling within the Interdisciplinary Centre for Security, Reliability and Trust (SnT). The SnT is renowned for its research and innovation in secure, reliable, and trustworthy ICT systems, fostering partnerships with industry and contributing to economic growth across Europe. This postdoc opportunity is situated at the intersection of machine learning, uncertainty quantification, and computational biomechanics, and is embedded within the Legato group in close collaboration with ARSPECTRA.
The successful candidate will design and implement Bayesian graph neural networks and convolutional neural networks as surrogates for high-fidelity biomechanical models. Responsibilities include quantifying and propagating uncertainty, developing strategies for real-time model selection and switching, integrating surrogate models with physics-based solvers (such as SOFA, FEniCSx, SOniCS), and deploying models on ARSPECTRA hardware with optimisation for embedded and GPU platforms. Collaboration with ARSPECTRA engineers and surgeons is key to creating a complete AR guidance pipeline, including tracking, SLAM, gaze, and user interface development.
Applicants must hold a PhD in machine learning, computational mechanics, computer science, applied mathematics, or a related field. Essential qualifications include strong experience with deep learning frameworks (PyTorch, JAX, TensorFlow), probabilistic methods, familiarity with graph neural networks, convolutional architectures, and surrogate modelling for physical systems. A solid understanding of PDE-based models or motivation to acquire this knowledge is required. Experience with real-time or edge deployment (CUDA, ONNX, TensorRT, FPGA) is advantageous, and the ability to work across disciplines—mechanics, ML, hardware, medicine—is important.
The University of Luxembourg offers a modern, dynamic, and international environment with high-quality equipment and close ties to industry and the Luxembourg labour market. The postdoctoral contract is for 12 months, full-time (40 hours per week), with a yearly gross salary of EUR 85,176. The institution promotes an inclusive culture and encourages applications from individuals of all backgrounds.
To apply, candidates should submit a CV, cover letter detailing motivation and alignment with the research topic, PhD diploma or expected defense date, transcript of university-level courses, and a list of publications. Applications must be submitted online via the HR system; email applications will not be considered. Early application is encouraged as applications are processed upon reception.
Funding details
Available
What's required
Applicants must hold a PhD in machine learning, computational mechanics, computer science, applied mathematics or a closely related field. Strong experience with deep learning frameworks such as PyTorch, JAX, or TensorFlow, and probabilistic methods is required. Familiarity with graph neural networks, convolutional architectures, and surrogate modelling for physical systems is expected. A solid understanding of PDE-based models or motivation to acquire this knowledge is necessary. Experience with real-time or edge deployment (CUDA, ONNX, TensorRT, FPGA) is advantageous. Ability to work across disciplines including mechanics, machine learning, hardware, and medicine is important. Applicants should submit a CV, cover letter, PhD diploma or expected defense date, transcript of university-level courses, and list of publications.
How to apply
Apply online through the University of Luxembourg HR system using the provided application link. Submit your CV, cover letter, PhD diploma or expected defense date, transcript of courses, and list of publications. Early application is encouraged as applications are processed upon reception. Applications by email will not be considered.
Ask ApplyKite AI

How do Indian students apply for this?
Sign in for free to reveal details, requirements, and source links.