This role demands both statistical depth and engineering proficiency – you will be expected to take models from research through to deployment, write code built for production, and use AI coding assistants fluently as part of how you get work done.
Responsibilities
Lead end-to-end development of predictive ML models. From data exploration and feature engineering through training, validation, deployment, and ongoing monitoring across engagement and clinical risk domains.
Apply strong statistical foundations to model design, feature selection, uncertainty quantification, and interpretation of results
Write production-grade Python code that is clean, tested, and built for maintainability and scale.
Use AI coding assistants to accelerate development, code review, and documentation without sacrificing quality or rigor.
Partner with product managers, data engineers, and software engineers to translate strategic questions and user behavior patterns into measurable, data-driven solutions.
Research and implement cutting-edge ML techniques spanning supervised and unsupervised learning, causal inference, deep learning, and reinforcement learning to tackle complex healthcare challenges.
Contribute to MLOps infrastructure: model serving, versioning, evaluation pipelines, and monitoring.
Design and interpret A/B tests and other experimental methodologies to measure the impact of models, features, and interventions.
Qualifications:
5+ years of hands-on experience developing, deploying, and maintaining ML models in production environments.
Bachelor's degree in Statistics, Computer Science, Applied Mathematics, Engineering, or a related quantitative field – a strong statistical foundation is essential for this role.
Deep expertise in statistics and probability: distributions, inference, hypothesis testing, Bayesian methods, causal inference, and experimental design, with the ability to apply these rigorously in a healthcare context.
Strong software engineering skills in Python: production-grade practices, version control, testing, and reproducibility.
Proficiency using AI coding assistants as a core part of the development workflow.
Expertise with ML frameworks such as PyTorch, scikit-learn, XGBoost, or LightGBM.
Experience building or working within ML pipelines end-to-end, including feature engineering, model registries, and deployment tooling.
Strong ability to translate complex statistical and technical findings into clear insights and recommendations for both technical and non-technical stakeholders.
Advantage:
Experience with cloud platforms (AWS preferred), containerization (Docker, Kubernetes), and MLOps platforms.
Prior work with healthcare or clinical datasets, including wearable device data, EMR, or claims data.
Experience with recommendation systems, reinforcement learning, or advanced causal inference.
