DATA SCIENTIST @ KILIMANJARO CHRISTIAN MEDICAL CENTRE
Kilimanjaro Christian Medical Centre (KCMC) is seeking a dedicated Data Scientist to join the Ophthalmology Department for a specialized program aimed at preventing sight loss from Diabetic Retinopathy through Artificial Intelligence. This five-year initiative focuses on screening diabetic patients across the Kilimanjaro and Arusha Regions to ensure early detection and referral for timely treatment. The role is based at KCMC Hospital in Moshi and offers a four-year employment contract.
The successful candidate will be responsible for developing, training, and optimizing deep learning models, including CNN and Vision Transformer architectures, specifically for retinal fundus image analysis. You will collaborate with clinical experts to manage large-scale datasets and implement explainable AI (XAI) techniques to build clinician trust. This position involves technical work in GPU-enabled Linux environments and the integration of AI tools into practical web or mobile applications to support clinical pilots.
The successful candidate will be responsible for developing, training, and optimizing deep learning models, including CNN and Vision Transformer architectures, specifically for retinal fundus image analysis. You will collaborate with clinical experts to manage large-scale datasets and implement explainable AI (XAI) techniques to build clinician trust. This position involves technical work in GPU-enabled Linux environments and the integration of AI tools into practical web or mobile applications to support clinical pilots.
Key Requirements
Master’s degree in Data Science, Artificial Intelligence, Machine Learning, Computer Science, or a related field.
Strong proficiency in Python for machine learning and scientific computing.
Hands-on experience in computer vision, particularly in medical image analysis or retinal imaging.
Proficiency in deep learning frameworks such as PyTorch or TensorFlow/Keras.
Practical experience with CNN architectures like ResNet, EfficientNet, and DenseNet.
Experience with Vision Transformer (ViT)-based architectures for image classification.
Expertise in image preprocessing pipelines, including normalization, augmentation, and artifact handling.
Proven experience with transfer learning and fine-tuning pretrained models on domain-specific datasets.
Ability to manage and annotate large-scale imaging datasets in collaboration with clinical experts.
Experience training models on GPU-enabled systems and working in Linux-based environments with Git.