Senior Data Scientist, Arine

• Master's or PhD in Statistics, Biostatistics, Epidemiology, Health Economics, Computer Science, a quantitative/physical science, or a related field
• Strong foundation in statistical inference and study design, and demonstrated expertise in causal modeling with observational data, e.g., propensity score methods, inverse probability weighting, instrumental variables, difference-in-differences, regression discontinuity, marginal structural models, and target trial emulation
• Demonstrated, hands-on experience with causal machine learning methods, e.g., double/debiased machine learning, causal forests, targeted maximum likelihood estimation (TMLE), or meta-learners (T-/X-/R-learners)—and familiarity with libraries such as WeightIt, MatchIt, grf, DoWhy, EconML, or CausalML
• Meaningful experience (3+ years) working with real-world healthcare data (e.g., medical and pharmacy claims or EHR data) and analyzing patient outcomes
• Experience handling the practical challenges of real-world data: missingness, confounding, selection bias, and measurement error
• Proficiency with R, Python (scikit-learn, pandas, numpy), and SQL
• Experience working cross-functionally to define analysis objectives and deliver analytical results
• Demonstrated ability to work independently, exercise good judgment, prioritize multiple projects, and problem-solve under tight deadlines and resource constraints
• Excellent written, interpersonal, and presentation skills, including the ability to convey complex technical concepts clearly to audiences with varying levels of technical understanding
• Ability to pass a background check
• Must live in and be eligible to work in the United States

Desirable

• This role involves deriving rigorous insights from large, diverse real-world health datasets to support Arine's mission to improve patient outcomes and lower the cost of healthcare at scale
• You'll go beyond prediction to estimate the real effects of medications and interventions on patient outcomes using modern causal inference and causal machine learning methods
• This is a dynamic role and an amazing opportunity to help shape the company from the ground up, with many growth opportunities
• The Data Science team works with feature-rich, high-volume clinical datasets and collaborates cross-functionally with an experienced team of in-house clinicians, health economics and outcomes researchers (HEOR), engineers, and digital health entrepreneurs
• Design and execute causal analyses of real-world health data to quantify the impact of medications and interventions on patient outcomes and costs
• Develop, validate, and deploy predictive and causal models and AI tools into Arine's medication management platform, with careful attention to bias, confounding, and generalizability
• Partner with clinicians and HEOR researchers to frame questions as well-defined causal estimands and translate findings into clinical and operational decisions
• Create presentations and reports communicating methods, assumptions, and results to the Data Science team and cross-functional stakeholders
• Participate in critical reviews within the Data Science team on everything from methods and study design to implementation strategy and code