Staff Data Scientist, Clinical Performance

This is a fully remote position, open to applicants in California, +1 more state.

📋 Description

• Drive the design and execution of sophisticated causal inference and statistical frameworks to evaluate and predict the effectiveness of Pearl’s clinical offerings and operational services.

• Create and develop scalable systems necessary for conducting thorough impact analyses, advancing beyond mere correlations to identify the genuine "Pearl Effect" on patient demographics.

• Construct predictive models to generate forecasts for clinical quality metrics, including eCQMs in MSSP and claims-based measures in REACH and LEAD.

• Collaborate with fellow Staff Data Scientists to enhance and validate patient risk models, ensuring that "rising acuity" indicators are effectively incorporated into our performance evaluation processes.

• Work in conjunction with Engineering and Analytics to develop solid data pipelines and machine learning infrastructure that facilitate automated, repeatable performance assessments.

• Partner with Product and Clinical Operations leaders to translate complex statistical insights into actionable narratives that shape product roadmaps and practice coaching initiatives.

• Design and supervise AI-driven agents that autonomously manage the complete lifecycle of our statistical models.

⛳️ Requirements

• A graduate degree (Masters or PhD) in a quantitative discipline such as Statistics, Economics, Biostatistics, or Epidemiology.

• Over 8 years of experience in results-oriented quantitative analysis.

• Demonstrated experience in applying causal inference methodologies (e.g., diff-in-diff, synthetic control, propensity score matching) in complex, real-world data settings.

• Experience in developing time-series forecasts or risk-adjustment models, with a solid understanding of how to define and assess a baseline versus an intervention effect.

• Expert-level skills in Python and SQL, with the capability to write production-quality code and design scalable data architectures.

• Experience in building or making significant contributions to scalable data science systems and infrastructure within a contemporary cloud environment (AWS, Snowflake, dbt). Recent in-depth experience with AWS Sagemaker is preferred.

• The ability to clarify the intricacies of a p-value, a risk score, or an identification strategy to a non-technical audience.

🏝️ Benefits

• We provide a competitive benefits package. More details can be found on our careers page.