Postdoctoral Associate (Data Scientist)

Project Overview

This project aims to develop and clinically validate a real-time blood analysis and diagnostic platform using an integrated microfluidic medical device. The platform uses precision microfluidic technology to process and profile the biological activity of white blood cells, which is related to inflammatory conditions ranging from diabetes and sepsis to leukemia.

The Postdoctoral Research Associate - Data Scientist will lead the acquisition, preprocessing, analysis, and modelling of medical device-generated data, and will work closely with clinicians, scientists, and engineers to translate AI/machine learning models into working, deployable software for clinical testing and point-of-care use.

This role offers a rare opportunity to bridge clinical data science, medical device engineering, and translational research, moving from experimental and clinical sample data to robust AI-enabled diagnostic workflows and deployable prototypes.

Responsibilities

The Postdoctoral Research Associate - Data Scientist is responsible for developing end-to-end data and AI/ML workflows for the medical diagnostic platform, from device data acquisition and signal/data preprocessing to model optimisation, validation, software integration, and deployment.

Responsibilities include:

• Work closely with clinicians, scientists, software engineers, mechanical/electrical engineers, and data scientists to define clinical use cases, data requirements, model outputs, and deployment workflows for the medical device platform.

• Design and implement reliable data acquisition pipelines from medical device hardware, sensors, imaging or signal outputs, and associated experimental or clinical metadata.

• Develop preprocessing, quality-control, annotation, feature-engineering, and data-management workflows for noisy, multimodal, longitudinal, or time-series biomedical data.

• Analyse experimental and clinical sample data to characterise device and biological performance, identify artefacts, benchmark platform performance, and support evidence generation for translational studies.

• Develop, train, validate, and optimise machine learning, deep learning, statistical, or hybrid models for diagnostic, predictive, or decision-support tasks using appropriate metrics, cross-validation, robustness checks, and uncertainty analyses.

• Translate research models into reproducible and deployable software components, including model inference pipelines, APIs, dashboards, reports, or lightweight user interfaces for clinical and laboratory testing.

• Support software-hardware integration for data acquisition, model inference, device feedback, and prototype deployment; assist with basic UX refinement based on clinician and end-user feedback.

• Maintain high-quality documentation of datasets, code repositories, model versions, experimental protocols, validation results, data dictionaries, and technical reports.

• Prepare manuscripts, presentations, grant reports, and invention disclosures; contribute to literature reviews, patent/IP searches, and responsible research dissemination where relevant.

• Support clinical study workflows by coordinating with clinical collaborators and applying good data governance practices for sensitive clinical and experimental data.

Requirements

• Ph.D. in Data Science, Computer Science, Artificial Intelligence/Machine Learning, Biomedical Engineering, Electrical Engineering, Bioinformatics, Statistics, Applied Mathematics, Computational Biology, or a related field. Candidates close to completion may be considered if the degree will be conferred before appointment.

• Demonstrated research experience in data science, machine learning, deep learning, signal/image processing, biomedical data analysis, time-series analysis, clinical AI, or related computational research.

• Strong programming skills in Python; experien