Senior Data Scientist - Risk Prediction Engine

CVS Health•New York, NY

1d•$111,240 - $222,480

About The Position

Join CVS Health’s healthcare data science team to develop the next generation of risk prediction models. The role uses analytical and machine learning skills to provide insights and model solutions to stakeholders across CVS Health and Aetna. The team works with petabytes of data and partners with actuarial experts to develop machine learning models for a growing range of use cases. The position calls for strong problem-solving and quantitative-analysis skills, algorithmic instincts, curiosity, and the ability to learn new domains quickly and test ideas efficiently. It also emphasizes practical use of AI tools to improve productivity, a working understanding of how large language models function, and thoughtful incorporation of AI into data science processes. The Senior Data Scientist develops and applies algorithms and statistical predictive models, selects analytical approaches and modeling techniques, and analyzes structured and unstructured data to address complex business problems. The role collaborates with business partners to understand goals and deliver predictive modeling, statistical analysis, reports, and performance metrics. It also presents and consults on analytics results, exchanges specialized information with peers and managers, explores large datasets using programming skills, and applies sound risk-management judgment when developing and validating models for business-critical decisions. The position requires a bachelor’s degree in a relevant discipline and at least three years of professional experience in data analytics, BI, data engineering, or applied data science, along with at least three years of SQL and Python/R experience. Extensive experience with SQL, Python, Spark, and cloud computing (AWS, GCP, or MS Azure) is described in the overview. The role is full time, with 40 anticipated weekly hours.

Requirements

Bachelor’s degree in Mathematics, Statistics, Computer Science, Business Analytics, Economics, Physics, Engineering, or a related discipline.
At least 3 years of professional experience in data analytics, business intelligence, data engineering, or applied data science.
At least 3 years of experience with SQL and Python/R.
Strong programming skills and knowledge of algorithms and predictive models.
Experience with SQL, Python, Spark, and cloud computing platforms such as AWS, GCP, or MS Azure.
Hands-on experience with large language models and AI/ML ecosystem tools, with an understanding of how these models work.

Nice To Haves

Master’s or PhD degree in Mathematics, Statistics, Computer Science, Business Analytics, Economics, Physics, Engineering, or a related discipline.
At least 5 years of professional experience in data analytics, business intelligence, data engineering, or applied data science.
At least 5 years of experience with SQL and Python/R.
Demonstrated experience using AI tools to accelerate personal workflow, together with strong algorithmic and risk-management acumen.

Responsibilities

Develop and/or use algorithms and statistical predictive models, and determine analytical approaches and modeling techniques to evaluate scenarios and potential future outcomes.
Analyze structured and unstructured data to solve multiple or complex business problems using advanced statistical techniques and mathematical analyses.
Collaborate with business partners to understand problems and goals and develop predictive modeling, statistical analysis, data reports, and performance metrics.
Develop and participate in presentations and consultations with existing and prospective constituents about analytics results and solutions.
Exchange complex information related to areas of specialization with internal and external peers and managers.
Use knowledge of algorithms and predictive models to investigate problems, detect patterns, and recommend solutions.
Use programming skills to explore, examine, and interpret large volumes of data in various forms.
Apply sound risk-management judgment when developing and validating models that inform business-critical decisions.
Ramp up on unfamiliar domains and methods, form hypotheses, and test them efficiently.
Incorporate AI tools and large language models into data science processes to improve productivity, efficiency, insight, and innovation.