Note: The job is a remote job and is open to candidates in USA. Harnham is seeking a Senior Data Scientist to develop statistical models and machine learning algorithms that improve patient enrollment and clinical trial management. The role focuses on predictive modeling, patient matching, model monitoring and bias detection, scalable data pipelines, regulatory compliance, and collaboration with machine learning engineering and other stakeholders.
Responsibilities
- Site Randomization Forecasting: Develop/enhance forecasting models for site randomization and enrollment trends, enabling better planning and resource allocation across trial sites
- Patient Matching/Ranking Algorithms: Support projects to build algorithms that intelligently match patients to (or rank patients for) appropriate clinical trials, enhancing recruitment efficiency and patient inclusion
- Develop Other Advanced Statistical Models: Create and refine predictive models (Bayesian inference, regression analysis, time-series forecasting) to address other key clinical trial challenges and improve decision-making
- AI Monitoring and Bias Detection: Implement processes to monitor machine learning models in production, detecting bias or performance drift and ensuring models remain fair, accurate, and compliant
- Data Pipeline & Tooling Development: Build and optimize data pipelines and analytical workflows using tools like AWS Athena, Redshift, SageMaker, and dbt, enabling scalable model training and deployment
- Regulatory Compliance in Data Science: Ensure all data science practices align with HIPAA, GDPR, and other privacy regulations, integrating compliance considerations into model development and data handling
- Cross-Functional Collaboration: Work closely with machine learning engineers, product managers, and other stakeholders to integrate models into products and clearly communicate insights and recommendations
Skills
- YOU MUST BE COMING FROM HEALTHCARE
- Built predictive models in production
- Monitored model performance after deployment
- Strong statistical foundations
- Experience influencing business decisions through modeling
- Excellent communication and stakeholder management skills
- Minimum of Master's or Ph.D. in Statistics, Data Science, Computer Science, or a related quantitative field (or equivalent professional experience)
- Minimum of 5+ years of hands-on data science or analytics experience
- Strong foundation in statistical modeling and machine learning techniques , including experience with Bayesian methods, regression analysis, and time-series forecasting
- Proficiency in evaluating model performance and bias, with the ability to implement AI monitoring tools and bias mitigation strategies to ensure ethical and reliable outcomes
- Advanced programming skills in Python (with libraries such as scikit-learn, PyMC, mlforecast, etc.) and SQL, as well as familiarity with data transformation tools like dbt
- Hands-on experience with cloud-based analytics and ML services, especially AWS tools (Athena for querying, Redshift for data warehousing, SageMaker for model development/deployment)
- Experience working with sensitive healthcare or clinical trial data under regulations like HIPAA and GDPR, demonstrating a deep commitment to data privacy and security best practices
- Preferably in a healthcare , clinical research, or other highly regulated data environment
- Domain Knowledge: Understanding of clinical research or health-tech environments is highly valuable, including insight into clinical trial operations and a passion for improving patient outcomes through data
Company Overview
Company H1B Sponsorship