Senior Staff Algorithm Engineer

Senior Staff Algorithm Engineer

BD is one of the largest global medical technology companies in the world. Advancing the world of health™ is our Purpose, and it's no small feat. It takes the imagination and passion of all of us—from design and engineering to the manufacturing and marketing of our billions of MedTech products per year—to look at the impossible and find transformative solutions that turn dreams into possibilities.

We are seeking a highly experienced Senior Staff Algorithm Engineer with deep expertise in physiological signal processing, biomedical sensor data, and classical machine learning to help develop next-generation medical technologies for continuous patient monitoring, disease detection, and predictive clinical insights.

In this role, you will design, develop, validate, and deploy algorithms that extract meaningful physiological parameters and clinical insights from complex, noisy, real-world sensor data. You will work with multi-modal data streams from monitoring sensors, bedside devices, wearable systems, electronic health records, and clinical datasets, with a primary focus on signal processing, statistical modeling, feature engineering, and interpretable machine learning approaches.

This role is ideal for an experienced engineer who understands both the physics of sensing and the physiology behind the signals, and who can translate raw waveform data into reliable, clinically useful metrics for regulated medical technology products.

Key Responsibilities

• Lead the design, development, validation, and deployment of algorithms for continuous physiological monitoring, new monitoring parameters and derived vital signs, signal quality assessment, artifact detection and rejection, multi-parameter trend analysis.
• Develop robust algorithms using physiological waveform and sensor data.
• Apply advanced signal processing techniques such as filtering and denoising, adaptive filtering, spectral analysis, time-frequency analysis, wavelet analysis, etc.
• Build classical machine learning and statistical models for clinically relevant algorithm outputs, including, logistic regression, support vector machines, random forests, gradient boosting methods, probabilistic models, clustering and anomaly detection, time-series forecasting models.
• Translate physiological and clinical understanding into meaningful algorithm features, performance requirements, model constraints, and interpretable outputs.
• Develop end-to-end algorithm pipelines for data ingestion, synchronization, waveform preprocessing, segmentation, signal quality assessment, feature extraction, model training, validation, performance characterization, and robustness testing.
• Work closely with clinical, systems engineering, software, embedded engineering, data science, regulatory, and quality teams to ensure algorithms are clinically meaningful, technically feasible, and suitable for regulated product development.
• Optimize algorithms for edge and embedded medical devices with constraints on latency, memory, compute, battery life, and real-time performance, as well as for cloud-based platforms supporting scalable analytics and retrospective evaluation.
• Support verification, validation, documentation, risk analysis, design controls, and clinical performance evaluation for regulated medical technology products.
• Conduct root-cause analysis of algorithm performance issues using real-world clinical data and field data.
• Contribute to intellectual property, technical strategy, algorithm roadmaps, scientific publications, and external technical engagement.
• Mentor junior engineers and help establish best practices for physiological signal processing and algorithm development.

Minimum Required:

• Bachelors degree in Electrical Engineering, Biomedical Engineering, Signal Processing, Computer Engineering, Applied Mathematics, Statistics, Physics, or a related quantitative or engineering discipline.
• 10+ years of industry experience in signal processing, algorithm development, biomedical engineering, medical devices, physiological monitoring, or related technical areas.
• Deep expertise in digital signal processing and algorithm development for real-world sensor data.
• Strong hands-on experience with physiological waveforms and biomedical signals such as ECG, PPG, respiration, blood pressure, capnography, or other patient monitoring signals.
• Strong understanding of human physiology, particularly as it relates to cardiopulmonary function, hemodynamics, respiratory physiology, patient monitoring, and acute care.
• Demonstrated experience developing algorithms from feasibility through productization, clinical validation, or deployment.
• Experience designing robust signal processing pipelines for noisy, artifact-prone, real-world physiological data.
• Strong background in feature engineering, statistical modeling, and classical machine learning.
• Experience evaluating algorithm performance using clinically relevant metrics such as sensitivity, specificity, positive predictive value, negative predictive value, AUROC, calibration, false alarm burden, limits of agreement, and robustness across subgroups and use conditions.
• Strong programming skills in Python, MATLAB, C, or C++.

Preferred Qualifications:

• Master's or PhD degree in a related quantitative or engineering discipline.
• Experience developing algorithms for regulated medical devices, patient monitoring systems, digital health products, or clinical decision support tools.
• Experience with medical device development practices, including design controls, requirements definition, risk management, verification and validation, clinical performance testing, usability and human factors considerations, and regulatory documentation.
• Familiarity with relevant medical device standards and regulatory expectations such as FDA guidance for medical device software, HIPAA, and healthcare data privacy/security requirements.
• Experience with sensor fusion across multiple physiological modalities.
• Experience with signal quality indices, artifact detection, missing-data handling, outlier detection, and robust estimation methods.
• Experience with embedded implementation constraints, including fixed-point arithmetic, memory optimization, computational complexity, real-time processing, and power consumption.
• Exposure to modern AI/deep learning methods
• Experience implementing or optimizing algorithms for embedded systems, edge devices, or real-time medical device platforms.
• Ability to clearly communicate algorithm design, assumptions, limitations, and performance results to engineering, clinical, regulatory, and business stakeholders.