About The Role
We are seeking an experienced and passionate Data Scientist with deep expertise in deep learning,medical imaging, and hands-on experience with foundation models. This is a technical contributor role where you will work at the intersection of healthcare and artificial intelligence, building innovative AI solutions that transform medical diagnostics, workflows, and patient outcomes.You will be instrumental in designing and developing cutting-edge AI/ML algorithms for imageanalysis, segmentation, classification, anomaly detection, and generative tasks in MagneticResonance Imaging (MRI).Project roles and responsibilities
Key Responsibilities
- Lead end-to-end development of deep learning models for medical imaging tasks – from data
curation and preprocessing to model training, evaluation, and deployment.
- Explore and fine-tune foundation models (e.g., vision transformers, multimodal models like
CLIP, BioGPT, MedSAM) for use in diagnostic and clinical imaging applications.
- Drive research and prototyping of novel architectures for image segmentation, detection,
and generation (e.g., UNet variants, GANs, autoencoders, diffusion models).
- Collaborate cross-functionally with radiologists, product managers, software engineers, and
regulatory teams to ensure clinical relevance, robustness, and compliance.
- Contribute to the development of scalable ML pipelines, model interpretability tools, and
performance monitoring systems.
- Publish findings in peer-reviewed journals or conferences and represent the company at
scientific and industry forums.
- Mentor junior data scientists and guide the team on best practices in model development,
validation, and documentation.Goals and deliverables
Required Qualifications
- PhD or master’s degree in computer science, Biomedical Engineering, Applied Mathematics,
or a related field.
- 5+ years of experience in data science or machine learning, with at least 3 years focused on
medical imaging.
- Strong experience in deep learning frameworks (TensorFlow, PyTorch) and model
architectures for computer vision.
- Practical exposure to foundation models, including prompt engineering, fine-tuning, and
domain adaptation.
- Proven ability to work with 2D/3D imaging datasets (DICOM, NIfTI), and medical imaging
toolkits (e.g., MONAI, SimpleITK, ITK-SNAP).
- Expertise in evaluation metrics specific to medical imaging (Dice, IoU, AUC, etc.) and
experience working with imbalanced datasets.
- Solid understanding of healthcare data compliance (HIPAA, FDA, MDR) and medical device
AI/ML lifecycle.
- Excellent problem-solving, communication, and leadership skills.
Preferred Qualifications
- Publications or patents in AI for healthcare or medical imaging domains.
- Experience with PACS/RIS systems, HL7/DICOM standards, and clinical workflows.
- Familiarity with LLMs or multimodal generative models in a clinical context.
- Exposure to MLOps, model deployment, and on-device inference optimization (e.g.,
TensorRT, ONNX, OpenVINO).
Skills: learning,ml,healthcare,models,foundation,data,medical imaging,dicom,deep learning