Data Scientist – AI / SaMD Products

About Us

EndeavourX is an entity of the National University Health System (NUHS), on a mission to scale some of NUHS’ most impactful AI solutions that have been developed and validated internally over the past few years. These products drive better care, operational efficiency, and clinician wellbeing.

We're a nimble, mission-driven team with access to leading clinical experts, real-world data, and deep public healthcare partnerships.

Why Join Us?

• Shape how cutting-edge AI already validated by a world-class hospital system is integrated into real clinical workflows
• Work alongside passionate clinicians, technologists, and policy thinkers
• Influence product, go-to-market, and strategy from day one
• Meaningful mission + real-world impact

Role Summary

The Data Scientist is responsible for developing, validating and maintaining AI/ML models that power EndeavourX’s healthcare products, including software as a medical device (SaMD). The role focuses on translating clinical and operational problems into robust, interpretable and production-ready models that can be safely deployed in regulated healthcare environments.

You will work closely with clinicians, software engineers and the cloud platform team to ensure models are not only accurate, but also deployable, monitorable and compliant.

Key Responsibilities

Problem Framing & Data Understanding

• Work with clinical, product and engineering stakeholders to translate healthcare problems into well-defined data science and modelling tasks.
• Understand clinical workflows, data provenance and data quality constraints relevant to healthcare datasets.
• Define modelling assumptions, limitations and appropriate evaluation strategies for clinical use cases.

Model Development & Evaluation

• Develop, train and evaluate machine learning and statistical models for healthcare applications.
• Select appropriate algorithms and features with consideration for model performance, robustness and interpretability.
• Design and execute validation strategies suitable for regulated or safety-critical use cases (e.g. temporal validation, cohort-based evaluation).
• Document model design decisions, performance characteristics and limitations clearly.

Production & Deployment Support

• Work with software engineers and the Cloud Architect to support deployment of models into production environments.
• Package models for inference, including feature preprocessing, versioning and reproducibility.
• Define requirements for model monitoring, drift detection and performance tracking post-deployment.
• Support troubleshooting and iteration of models based on real-world performance.

Quality, Governance & Regulated Delivery

• Follow model development and documentation practices aligned with regulated healthcare delivery (e.g. traceability, version control, change management).
• Participate in design reviews, risk discussions and assessments related to model behaviour, bias, safety and reliability.
• Support preparation of documentation required for internal review, audits or regulatory submissions.

Collaboration & Knowledge Sharing

• Collaborate closely with clinicians, software engineers and product stakeholders to deliver end-to-end solutions.
• Communicate model results, trade-offs and limitations clearly to technical and non-technical audiences.
• Contribute to improving data science standards, tooling and best practices within the team.

Job Requirements

Experience & Skills

• 4–8 years of experience in data science, machine learning or applied statistics roles.
• Strong foundation in machine learning, statistics and data analysis.
• Proficiency in Python and common data science libraries (e.g. pandas, NumPy, scikit-learn, PyTorch, TensorFlow).
• Experience working with real-world, messy datasets and imperfect labels.
• Ability to explain model behaviour, assumptions and limitations clearly.
• Experience applying data science or ML in healthcare, medtech, life sciences or other regulated or safety-critical domains preferred.
• Familiarity with model governance, validation or documentation practices in regulated environments would be an advantage.