Job Description
Lead data scientists analyze complex datasets using machine learning models to optimize commercial strategies and improve patient outcomes at EMD Serono. They design supervised models for regression and classification, apply causal inference to observational data, and build scalable AI pipelines for high-dimensional healthcare datasets. Mentors guide junior scientists on advanced techniques within commercial pharma settings.
EMD Serono develops medicines in oncology, neurology, and fertility as part of Merck Group's Healthcare division, operating across 6 continents. The team focuses on innovative treatments to prolong lives, with a diverse culture supporting career advancement.
Responsibilities include partnering with commercial, medical, and IT teams to address key problems, validating models through hypothesis testing and feature engineering, and deploying Python-based systems using containers on AWS. Scientists leverage knowledge of claims and EMR data, communicate actionable recommendations, and prioritize impacts aligned with strategic goals.
The on-site role in Seaport MA offers a pay range of $126,800 to $191,700, eligible for bonuses, with 8 a.m. to 5 p.m. hours. Benefits include health insurance, paid time off, retirement contributions, and perks. Preferred candidates have 6+ years in pharma with expertise in marketing mix models and GenAI for text features.
Responsibilities
- Collaborate with Commercial, Medical, and IT teams to identify high-impact problems and deliver analytics solutions
- Design, validate, and interpret supervised and unsupervised models for decision-making
- Apply causal inference to experimental and observational data for strategy optimization
- Build scalable AI/ML pipelines for large, high-dimensional datasets
- Mentor junior data scientists and foster culture of excellence
- Leverage knowledge of US healthcare and pharma landscapes with claims and EMR data
- Translate complex analytical findings into actionable business recommendations
- Deploy Python-based machine learning models in production using containers and shell scripting
- Prioritize high-impact problems aligned with strategic objectives
- Communicate clearly across diverse stakeholders
Requirements
- Master’s degree in Statistics, Data Science, Mathematics, Physics, Econometrics, Operations Research, or related field
- 4+ years experience as data scientist in commercial setting (pharma preferred)
- Strong expertise in supervised/unsupervised learning, causal inference, scalable ML pipelines
- Proficiency in Python (pandas, scikit-learn), SQL, Git, Linux, AWS