Senior Scientist, AI / ML & Computer Vision

Key Responsibilities

• Design, train, fine-tune, and validate deep learning computer vision models for medical imaging applications.
• Develop AI capabilities for image quality assessment, anatomical segmentation, landmark detection, geometric measurement, patient screening, procedural planning, and clinical decision support.
• Advance the development of in-house medical imaging foundation models through large-scale supervised, self-supervised, and transfer-learning approaches.
• Ensure models generalize across multiple imaging vendors and acquisition protocols, not only a single reference dataset.
• Partner closely with AI Evaluation, Quality, Regulatory Affairs, and Software Engineering teams to support verification, validation, risk assessment, and regulatory documentation activities.
• Rigorously evaluate models for systemic bias and stand up MLOps frameworks to monitor for performance drift or shift across different datasets.
• Drive research and experimentation to explore new AI and machine learning techniques, tools, and frameworks.
• Collaborate with data scientists, software engineers, product managers, and business leaders to define requirements and develop AI and machine learning solutions.
• Design, develop, and deploy scalable, efficient AI and machine learning models for prototypes and production use.
• Build end-to-end data pipelines for collecting, processing, and analyzing large-scale datasets.
• Optimize model performance to improve robustness, scalability, and efficiency.
• Participate in agile development processes, including sprint planning, daily stand-ups, prototype demonstrations, and milestone updates.
• Ensure code and model development are well-documented and follow engineering best practices.

What You'll Need (Required)

• Bachelor's degree in engineering or a related technical field, plus four years of AI / ML engineering experience, including successful collaboration with cross-functional teams on complex, enterprise-level, or novel system implementations.
• Proven experience designing, training, and validating deep learning computer vision models end to end.
• Strong experience with medical image analysis, including one or more of the following: segmentation, registration, landmark detection, image quality assessment, anatomical measurement, or disease classification.

What Else We Look For (Preferred)

• MS or PhD (preferred, but not required) in computer vision, biomedical engineering, or a related field, or equivalent industry depth.
• 5 to 10 years' experience in computer vision or medical image analysis, with direct experience handling failure modes, including generalizability across different datasets, institutions, and vendors.
• Experience working with DICOM imaging data and large-scale imaging datasets.
• Proficiency with common machine learning, deep learning, and computer vision libraries, such as scikit-learn, NumPy, SciPy, PyTorch, TensorFlow/Keras, OpenCV, scikit-image, PIL, and torchvision.
• Strong knowledge of machine learning algorithms, statistics, and data structures.
• Experience with modern computer vision deep learning model architectures and learning paradigms such as transformers (including vision transformers), convolutional neural networks (CNNs, including U-Nets), diffusion models, and self-supervised learning (e.g., masked autoencoders and contrastive learning frameworks).
• Experience with cloud computing environments (particularly Amazon Web Services and Microsoft Azure), as well as remote computing and distributed computing.
• Proficiency in Python; experience with R, SQL, Julia, Rust, C++, or a similar language is also valued.
• Experience working with data platforms, including Snowflake, Databricks, and/or Palantir.
• Experience deploying machine learning solutions into production systems.
• Experience supporting the development of regulated software, Software as a Medical Device, or AI-enabled medical devices.
• Familiarity with design controls, verification and validation activities, risk management, and Good Machine Learning Practice (GMLP).
• Demonstrated technical leadership through publications, patents, open-source contributions, product launches, or industry recognition.
• Experience with version control systems such as Git and with agile development methodologies.
• Preferred experience collaborating with executive-level management, external vendors, and team members across regional and global offices.
• Effective communication, collaboration, and problem-solving skills.
• Excellent attention to detail and the ability to manage competing priorities in a fast-paced environment.