Machine Learning Internship - Multimodal Radiological Foundation Models

About Raidium

Raidium is developing the most advanced radiological LVLM (Large Vision Language Model); The first version of our Foundation model, Curia, is now the state-of-the-art copilot of the new generation of radiological image manipulation software.

The internship - Multimodal Radiological Foundation Models

• Foundation models offer a promising approach to building generalist models, capable of solving multiple tasks in zero-shot or few-shot settings. They are pre-trained on large amounts of unlabeled data and can be efficiently adapted to many downstream tasks. For medical imaging, such models include MedImageInsight or BioMedCLIP. At Raidium, we are building our own foundation models for radiology, for 3D CT and MRI imaging, that can then be used for many medical tasks such as image segmentation, detection, or classification.
• We released our first foundation model, Curia, a state-of-the-art vision encoder for radiology images. This model takes only images as input, and for the next step, we will focus on integrating the language modality, similarly to MERLIN and Pillar-0. This will help to unlock novel text-based radiological workflows.
• In this internship, you will work on 2D and 3D multimodal (vision and language) foundation models to integrate multiple modalities (X-Ray, CT, MRI) and reports into our base models. You will leverage mDNSResponderRaidium’s unique dataset (130TB) of radiological exams and reports.

You will:

• Design and experiment with multimodal foundation model architectures
• Integrate novel pre-training datasets to improve performance or add novel modalities
• Adapt and benchmark those approaches on new multimodal downstream tasks
• Interact with Raidium’s radiologist userbase to define the model’s requirements
• You will be managed by Corentin Dancette, Lead ML Researcher at Raidium

You

• Finishing MSc in Mathematics / Computer Science / Electrical Engineering;
• Proficiency with statistics / Machine Learning algorithms
• Proficiency with Deep Learning, Computer Vision algorithms and/or NLP algorithms
• Proficiency with Python
• Willingness to work in the healthcare industry
• Authorization to work in France

Pluses

• Experience in an agile work environment
• Publication history in top-tier Machine Learning or healthcare journals
• Experience in healthcare and/or with the manipulation of radiological images
• Experience with Self-Supervised Learning and Transformers
• Experience with HPC clusters and GPU-based infrastructures

Why join us

• Have a real and positive impact on people's lives
• Apply and improve the latest Deep Learning technologies to build an inspiring product
• Be in contact with radiologists in our partner center
• Be among the first employees of Raidium
• Work with a team of internationally recognized experts
• Work with a diverse team of engineers and medical doctors
• Competitive salary
• Access to premium computing hardware

€2,000 - €2,000 a month

Duration: 6 monthsExpected start date: March 2026Location: Hôpital Cochin, Paris 14