Staff Machine Learning Engineer
Posted Updated
Description
Key Responsibilities
- Lead the design, development, validation and deployment of AI/ML algorithms for continuous physiological monitoring, novel vital sign and physiological parameter development, disease detection and risk stratification and early warning systems.
- Develop algorithms using multi-modal data sources, including physiological waveforms and time-series data such as PPG, blood pressure, capnography and other monitoring signals, bedside and wearable sensor data, electronic health records and structured clinical data, etc.
- Apply advanced analytical approaches, including:
- Classical machine learning models
- Statistical modeling and probabilistic inference
- Time-series modeling
- Signal processing and feature engineering
- Deep learning architectures
- Multimodal AI models
- Transformer-based models and foundation-model approaches where appropriate
- Translate clinical and physiological understanding into robust algorithm design, including feature selection, model architecture, performance targets, and clinically interpretable outputs.
- Build end-to-end algorithm development pipelines for data ingestion, signal quality assessment, annotation, feature extraction, model training, validation, robustness testing, and post-market performance monitoring where applicable.
- Partner with clinical, medical affairs, regulatory, quality, and product teams to ensure algorithms are developed with appropriate clinical context, usability, safety, and regulatory considerations.
- Develop and optimize algorithms for cloud environments and for edge or embedded medical devices, accounting for latency, memory, compute, power, cybersecurity, and reliability constraints.
- Support verification, validation, documentation, risk analysis, and design controls for regulated medical technology products.
- Contribute to intellectual property generation, technical strategy, research roadmaps, and external scientific engagement.
Required Qualifications
- Bachelor's in Electrical Engineering, Biomedical Engineering, Computer Science, Data Science, Applied Mathematics, Statistics, Computational Biology, or a related engineering or quantitative field.
- 7+ years of industry experience in AI/ML, algorithm development, biomedical signal processing, healthcare analytics, medical devices, or related technical areas.
- Deep expertise in machine learning and AI model development, including both classical and modern approaches.
- Strong hands-on experience with physiological time-series data, biomedical signals, medical device data, or clinical datasets.
- Understanding of human physiology, especially as it relates to patient monitoring.
- Demonstrated experience developing algorithms from early feasibility through productization or deployment.
- Experience working with multi-modal healthcare data, such as sensor signals, EHR data, imaging data, lab data, and clinical outcomes.
- Strong programming skills in Python and experience with ML/AI frameworks such as PyTorch, TensorFlow, scikit-learn, or equivalent tools.
- Experience with cloud-based algorithm development and deployment using platforms such as Azure, AWS, or Google Cloud Platform.
- Experience optimizing models for deployment on constrained environments, including embedded systems, edge devices, or near-real-time medical technology platforms.
- Strong understanding of model evaluation, including sensitivity, specificity, AUROC, calibration, false alarm burden, clinical utility, robustness, and generalizability.
- Excellent communication skills with the ability to explain complex technical concepts to engineering, clinical, regulatory, and business stakeholders.
Preferred Qualifications
- Master's or PhD degree Electrical Engineering, Biomedical Engineering, Computer Science, Data Science, Applied Mathematics, Statistics, Computational Biology, or a related engineering or quantitative field.
- Experience developing AI/ML algorithms for regulated medical devices, digital health products, clinical decision support tools, or Software as a Medical Device (SaMD).
- Familiarity with medical device development practices, including design controls, risk management, verification and validation, human factors, clinical performance evaluation, and regulatory documentation.
- Experience with signal quality assessment, artifact detection, missing-data handling, sensor fusion, uncertainty quantification, and explainable AI.
- Familiarity with MLOps, model lifecycle management, version control, data governance, automated testing, and post-deployment monitoring.
Skills
- AI
- Analytics
- AWS
- Azure
- Cloud
- Cybersecurity
- Data Governance
- Data Ingestion
- Data Science
- Deep Learning
- Embedded Systems
- Feature Engineering
- GCP
- Machine Learning
- MLOps
- Model Evaluation
- Python
- PyTorch
- scikit-learn
- Sensor Fusion
- Signal Processing
- Statistics
- TensorFlow
- Test Automation
- Time Series
- Version Control
Sign in to read and join the discussion.