Software AI Engineer 4
Hologic Careers
Summary
Hologic is seeking a Software Algorithm Engineer 4 to design, train and validate deep learning models for cytology on the Genius Digital Diagnostics System. This role owns the cell-level CNN classifier, nuclear-to-cytoplasmic (NC) ratio segmentation pipeline, and the technical evidence needed to support FDA and other regulatory submissions. The engineer serves as the technical lead for model design and verification under design controls, working closely with cytopathologists, imaging scientists, regulatory and quality teams.
Job description
Key Responsibilities
- Design, train and tune multi-class CNNs to classify cells and aggregate predictions into specimen-level diagnostic categories.
- Develop multi-task models with shared encoders and feature heads for diagnostic class, cytomorphologic features and NC ratio category.
- Build nucleus and cytoplasm segmentation networks to measure NC ratio and nuclear area, including overlapping cells in clusters.
- Own the data pipeline, including patient-grouped splits, color profile application, class balance and imaging metadata.
- Run disciplined experiments, benchmark lightweight backbones against larger reference models and define evaluation metrics and reports.
- Collaborate with pathologists on labeling protocols, inter-observer agreement and adjudication processes.
- Prepare design documentation, verification/validation protocols and technical content for regulatory submissions.
- Mentor engineers and establish coding, reproducibility and MLOps standards.
- Ensure model performance and interpretability, including Grad-CAM checks and feature outputs that align with pathologist expectations.
- Support regulatory strategy for AI-enabled medical devices under design controls and PCCP guidance.
Qualifications
Education: MS or PhD in computer science, biomedical engineering, electrical engineering or a related field, or BS with equivalent experience.
Experience: 7+ years of software development, including 4+ years building and deploying deep learning models for computer vision. Coaching and mentorship experience a plus.
- Expert Python and PyTorch (or TensorFlow), including CNN fine-tuning, transfer learning and segmentation (e.g., U-Net, segmentation_models_pytorch).
- Experience with imbalanced, multi-class and multi-task problems, and metrics such as per-class sensitivity, F1, kappa and AUROC.
- Experience with medical or microscopy imaging, including color handling, stain variation and high-resolution tiling.
- Strong discipline in data splitting, leakage prevention, experiment tracking and reproducible training.
- Clear written communication for technical reports and design documentation.
- Preferred: digital pathology or cytology AI experience (ideally urine cytology); experience with FDA 510(k), De Novo, PMA or EU IVDR; familiarity with IEC 62304, ISO 13485, ISO 14971, 21 CFR Part 820 and FDA PCCP guidance.
- Preferred: ICC color management, stain deconvolution and scanner color calibration; cell instance segmentation tools (StarDist, Cellpose) and annotation tools (QuPath, CVAT, napari).
- Preferred: model optimization for edge or embedded inference (quantization, ONNX, TensorRT) and experience leading or technically guiding a small team.
Requirements
- MS or PhD in computer science, biomedical engineering, electrical engineering or a related field, or BS with equivalent experience
- 7+ years of software development
- 4+ years building and deploying deep learning models for computer vision
- Expert Python and PyTorch (or TensorFlow), including CNN fine-tuning, transfer learning and segmentation
- Experience with imbalanced, multi-class and multi-task problems, and metrics such as per-class sensitivity, F1, kappa and AUROC
- Experience with medical or microscopy imaging, including color handling, stain variation and high-resolution tiling
- Strong discipline in data splitting, leakage prevention, experiment tracking and reproducible training
- Clear written communication for technical reports and design documentation
- Preferred: digital pathology or cytology AI experience
- Preferred: experience with FDA 510(k), De Novo, PMA or EU IVDR
- Preferred: familiarity with IEC 62304, ISO 13485, ISO 14971, 21 CFR Part 820 and FDA PCCP guidance
- Preferred: ICC color management, stain deconvolution and scanner color calibration
- Preferred: cell instance segmentation tools (StarDist, Cellpose) and annotation tools (QuPath, CVAT, napari)
- Preferred: model optimization for edge or embedded inference (quantization, ONNX, TensorRT)
- Preferred: experience leading or technically guiding a small team
- Coaching and mentorship experience a plus
Benefits
- Comprehensive training
- Continued development and training
- Bonus eligible
Company overview
Hologic, Inc. is a leading global medical technology company founded in 1985 and headquartered in Marlborough, Massachusetts. The company specializes in developing and manufacturing innovative diagnostic products, medical imaging systems, and surgical solutions with a particular focus on advancing women's health and well-being. Hologic operates across three core business segments: Breast & Skeletal Health, Diagnostic Solutions, and GYN Surgical Solutions. The company's mission is to enable healthier lives everywhere, every day through science-based certainty in early detection and treatment. Hologic is renowned for its clinically superior products that help detect, diagnose, and treat illnesses earlier and more effectively, with a strong emphasis on women's health issues including breast cancer, cervical cancer, and gynecological conditions. The company employs approximately 5,000-10,000 professionals globally and maintains a significant presence in the medical technology sector, consistently pushing the boundaries of innovation in healthcare diagnostics and treatment solutions.