R&D Internship

We are a neurotech company developing personalized non-invasive brain stimulation therapies using transcranial Electrical Stimulation (tES). At the core of our workflow are biophysical head models that allow us to precisely predict and optimize electric current flow through each patient's unique anatomy. These models are derived from structural brain MRI by segmenting individual tissues and building a geometrically realistic finite element model.

While this approach is well established, a few challenges are yet to be addressed: incomplete scan coverage, imaging artefacts, and anatomical anomalies such as surgical resections or implants can disrupt the pipeline adding time and manual effort. Deep learning offers a promising path to address these challenges and make our workflow faster, more robust, and more scalable.

You will join our team to help develop and evaluate deep learning solutions for structural MRI processing, including semantic segmentation and image restoration. Your tasks will involve:

• Training DL models.
• Running systematic model evaluation and benchmarking.
• Writing technical reports documenting methods and results.

We are looking for a motivated MSc or final-year BSc student with one of the following profiles:

• A Biomedical Engineering background with hands-on experience in deep learning and a strong interest in medical image analysis
• A Deep Learning or Computer Vision background with a genuine interest in applying your skills to clinical and medical imaging problems.

Knowledge of Python is a must. Familiarity with PyTorch and medical imaging libraries (Monai or similar) is a plus. Prior experience with MRI data or segmentation tasks is welcome but not required.