Data Scientist

Responsibilities:

• Model Development & Prototyping: Design, train, and validate machine learning and statistical models focused on risk stratification, disease progression, treatment intelligence, and healthcare recommendations.
• Longitudinal EHR Feature Engineering: Translate temporal clinical touchpoints—such as diagnostic records, symptoms, lab investigations, and prescriptions—into robust features for predictive models and generative AI systems.
• Unstructured Data Pipeline Design: Build models and pipelines capable of extracting insights from unstructured healthcare records, doctor notes, and medical terminologies.
• Problem Scoping & Hypothesis Testing: Frame open-ended clinical questions into clear, measurable machine learning objectives; define appropriate targets, data requirements, and success metrics.
• Production Integration & Monitoring: Work alongside engineering teams to operationalize prototypes into production environments and establish continuous model performance tracking.
• Comprehensive Model Evaluation: Construct evaluation systems that assess offline metrics alongside real-world clinical validity, model calibration, algorithmic bias, and robustness.
• Cross-Functional Collaboration: Partner with domain experts (clinicians) and technical stakeholders to ensure solutions directly enhance healthcare delivery and operational outcomes.

Required Skills:

Primary Skillset:

• Machine Learning & Statistical Modeling (Model Design, Evaluation, Calibration)
• Python & Core Data Science Stack (Pandas, NumPy, Scikit-learn, PyTorch or similar)
• Advanced SQL & Complex Querying
• Working with Large-Scale, Messy & Longitudinal Data
• Problem Formulation (Translating ambiguous domain/business problems into concrete ML setups)

Secondary Skillset:

• Healthcare/EHR/Claims Data Processing & Clinical Ontologies
• Clinical NLP & Medical Language Models (including LLMs/Generative AI)
• Advanced Analytics: Time-Series Analysis, Survival Analysis, & Causal Inference
• Big Data Frameworks (e.g., PySpark)
• Production ML Deployment & Performance Monitoring
• Technical Communication & Cross-Functional Stakeholder Alignment