About Caption Health
Caption Health’s mission is to detect disease early – when there is the highest potential for impact – by leveraging artificial intelligence and ultrasound. Our breakthrough AI platform enables any healthcare professional to perform high-quality ultrasound exams for early disease detection, in convenient and lower-cost outpatient settings including patients’ homes. It was recognized as one of TIME’s 100 Best Inventions of 2021 and one of Fast Company’s Next Big Things in Health Tech.
Through our work with health plans, providers, patients, and industry partners, we are transforming care, expanding access, and reducing costs.
We are seeking an experienced Machine Learning Engineer to join our team and make an impact! This role is responsible for developing, benchmarking, validating, and deploying a wide variety of deep neural network architectures for the purpose of extracting clinically-relevant knowledge from ultrasound images.
Responsibilities
- Develop deep learning model training and testing pipelines to assess the performance on clinically-relevant image processing tasks.
- Organize data for labeling and annotation and subsequently integrate datasets into training pipelines as part of an iterative model improvement process.
- Keep up with literature on state-of-the-art deep learning techniques in order to implement the latest into our networks and pipelines.
- Develop machine-learning algorithms on a breadth of software frameworks (Keras, TensorFlow, PyTorch, scikit-learn).
- Contribute to deployment of models on a diversity of hardware platforms, including mobile devices.
- Read relevant medical literature to be able to develop sound validation procedures/metrics.
- Share theoretical and practical ideas in deep learning and machine learning with the rest of the team.
- Perform other duties as assigned.
Requirements
- Minimum bachelor’s degree (master’s or Ph.D. preferred) in Computer Science, Electrical/Biomedical Engineering, Physics, Neuroscience, Statistics, Mathematics, or related fields.
- 5+ years of combined academic and/or industry experience in training, testing, developing, and analyzing deep neural networks (recurrent, convolutional, spatiotemporal, attention-based).
- Experience in developing and tuning custom neural network components such as layers and losses based on scientific literature.
- Deep theoretical and practical knowledge of machine learning principles and deep neural network techniques (separable and 3D convolutions, inference acceleration frameworks, network compression, adversarial training, etc.).
- Knowledge of computer vision and image processing techniques and methods.
- Experience with Python and the Python scientific stack (numpy, scipy, matplotlib, pandas, scikit-learn, scikit-image).
- Advanced experience with at least one major deep learning framework (Tensorflow, Keras, PyTorch, etc.).
- Experience with writing production code, testing frameworks, and code review process.
- Strong teamwork ethic, communication skills, and passion for learning.
- Proficient with Microsoft 365 or similar software.
- Preferred qualifications:
- Knowledge of C++ in an industry context is a plus.
- Experience working with medical imaging data and familiarity with the DICOM data format.
- Publications in top-tier machine learning journals or conferences is a plus.
Caption Health is an Equal Employment Opportunity employer that proudly pursues and hires a diverse workforce. Caption Health does not make hiring or employment decisions on the basis of race, color, religion or religious belief, ethnic or national origin, nationality, sex, gender, gender-identity, sexual orientation, disability, age, military or veteran status, or any other basis protected by applicable local, state, or federal laws or prohibited by Company policy. Caption Health strives for a healthy and safe workplace and strictly prohibits harassment of any kind. Pursuant to the San Francisco Fair Chance Ordinance and other similar state laws and local ordinances, and its internal policy.
