Principal Software Algorithm Engineer
Our client is seeking a Principal AI Engineer - Digital Pathology in Marlborough, MA. This is a direct hire role with a hybrid workstyle.-Design, train and tune multi-class CNNs that assign cells to diagnostic categories and aggregate cell predictions into a specimen-level category.- Build multi-task models with a shared encoder and separate heads for diagnostic category, cytomorphologic features and NC ratio category.- Develop nucleus and cytoplasm segmentation networks to measure NC ratio and nuclear area, including handling of overlapping cells in clusters.- Own the data pipeline: patient-grouped splits, ICC color profile application, export settings, class balance and per-image metadata (staining program, site, instrument, calibration profile).
Education:
MS or PhD in computer science, biomedical engineering, electrical engineering or a related field, or BS with equivalent experience.
Experience:
10+ years of software development, including 5+ years building and deploying deep learning models for computer vision.
Skills:
Expert Python and PyTorch (or TensorFlow), with hands-on CNN fine-tuning, transfer learning and segmentation (e.g. U-Net, segmentation_models_pytorch).- Experience with imbalanced, multi-class and multi-task problems, and with metrics such as per-class sensitivity, F1, kappa and AUROC.- Experience with medical or microscopy images, including color handling, stain variation and high-resolution tiling.