Oakville, Ontario, Canada
Biomedical & Software Engineer passionate about designing and validating innovative medical technologies. Experienced in software and systems engineering, leading the development of medical systems and software architectures for remote health monitoring. My work spans real-time data acquisition, multi-sensor integration, and full stack development for BLE-enabled wearable systems used in R&D, clinical and research environments. Driven by a commitment to accessibility and impact, my long-term goal is to help advance equitable access to medical devices and digital health technologies.
Develop backend APIs and cross-platform apps (Python/FastAPI, React Native) for connected health devices. Build BLE/USB SDKs for multi-sensor wearables and integrate data pipelines that enable real-time streaming of ECG, IMU and Pressure data, analytics, and ML model deployment. Support the full product development lifecycle for medical-electrical systems such as pressure-sensing, heat therapy, and multi-sensor wearable devices. Collaborate across hardware, firmware, and textile teams to integrate and validate biomedical systems, ensuring reliability and scalability for clinical and research use cases.
Worked on the OSAP platform, conducting data synchronization testing and writing SQL queries across Oracle and DB2 databases to verify data integrity. Built Power BI dashboards and visualizations to support reporting and analysis for financial aid workflows.
Worked part-time during the academic year on the front-end development of a Python-based desktop application for chronic pain assessment. Implemented pose estimation and visual recognition using MediaPipe, enabling motion-based pain predictions for users. Collaborated on the development and testing of deep learning models (CNNs) for emotion classification using TensorFlow and Keras, improving model accuracy and robustness.
Developed the front-end of a mobile application for pain prediction in chronic low back pain (CLBP) patients using React Native with a Node.js backend. Integrated REST APIs, designed multi-screen user flows, and implemented a TensorFlow-based ML pipeline using OpenPose and PoseNet for real-time pose estimation and keypoint detection.