CareFirst Careers

Senior Data Scientist FEP

This job posting is no longer active

Resp & Qualifications


As a Data Scientist, you will:

  • Join a brand new team of machine learning researchers with an extensive track record in both academia and industry.
  • Bring a combination of mathematical rigor and innovative algorithm design to create recipes that extract relevant insights from billions of rows of data to effectively & efficiently improve health outcomes.
  • Create thoughtful solutions that engage and empower members to make more informed decisions about their health
  • Develop statistical applications that can be reproduced and deployed on enterprise platforms.
  • Develop functional means for measuring the quality of healthcare members receive annually.
  • Learn, develop, and apply new techniques in the intersection of math, probability, and optimization
  • Interact with and report to an audience that includes Directors, Vice-Presidents and the C-level executives
  • Collaborate with external clients and internal departments to understand company needs and devise possible solutions leveraging the power of Machine Learning.
  • Explain the results and implications of classical statistical analyses and machine learning methods to non-technical business audiences, orally and in writing.
  • Build tools and support structures needed to analyze data, perform elements of data cleaning, feature selection and feature engineering and organize experiments in conjunction with best practices.
  • Develop and validate statistical and machine learning models, including predictive analytics and anomaly detection models, to identify potential fraud, waste, or abuse in medical claims data, primarily using Python and Spark/Scala. 
  • Assess the effectiveness and accuracy of new data sources and data gathering techniques.
  • Assist with the evaluation of data analytic vendors and tools.


Some examples of the problems you might tackle in your new role:

  • How to recognize fraudulent claims using anomaly detection models, to identify potential fraud, waste, or abuse in medical claims data, to avoid loss of revenue, primarily using Python and Spark/Scala?
  • How do we leverage our data that allow us to understand the unique needs of our members to support seamless care delivery that engages our members, supports our providers and improve health outcomes?



The Data Scientist Analytics role has work across the following four areas:

Exploratory Analysis

  • Understanding ecosystems, user behaviors, and long-term trends
  • Evaluating and defining use cases for potential product ideas
  • Identifying levers to help move key metrics
  • Evaluating and defining metrics
  • Building models of user behaviors for analysis or to power production systems

Data Infrastructure & Machine Learning

  • Working in Hadoop and HIVE primarily, sometimes DB2
  • Authoring pipelines via SQL and Spark or Python based ETL framework
  • Building key data sets to empower operational and exploratory analysis
  • Performing and automating analyses using statistical language Python

Product Operations

  • Designing and evaluating experiments monitoring key product metrics, understanding root causes of changes in metrics
  • Building and analyzing dashboards and reports

Product Leadership

  • Influencing business partners through presentation of data-based recommendations
  • Communicating of state of business, experiment results, etc. to internal and external partners
  • Spreading best practices to analytics teams
  • Proposing what to build in the next roadmap

This position is also subject to being "on call" for emergency situations requiring immediate resolution.  Travel between all CareFirst locations may be required.





Minimum Qualifications:

Required experience, abilities and skills:

  • Master’s degree in Computer Science, Statistics, Operations Research, Mathematics or related field or equivalent.
  • 7+ research or industry experience.
  • Proven ability to influence cross-functional teams without formal authority.
  • Advanced proficiency in Python and Spark/Scala for classical statistical analysis and data modeling, machine learning and ETL processes.
  • Ability to write production-ready code including documentation and unit tests. 
  • Experience with machine learning methods like k-nearest neighbors, random forests, ensemble methods and more.
  • Proficiency in data science modeling – AI, Machine Learning, Deep Learning, Decision Trees, Random Forest, Neural Networks, Supervised/Unsupervised Learning, Forecasting, Predictive Modeling and Clustering. 
  • Strong background in machine learning using unsupervised and supervised methods.       
  • Deep knowledge of fundamentals of machine learning, data mining and statistical predictive modeling, and extensive experience applying these methods to real world problems 
  • Fluency in SQL and other programming languages. Some development experience in at least one scripting language (PHP, Python, Perl, etc.)
  • Proven experience of using Python Machine Learning & Data Pre-processing Libraries. (Scikit Learn, Numpy, Pandas)
  • Ability to initiate and drive projects to completion with minimal guidance
  • The ability to communicate the results of analyses in a clear and effective manner


  • PhD is preferred
  • Preferred experience with a statistical package such as R, MATLAB, SPSS, SAS, Stata, etc.
  • Proficiency with healthcare analytics and data structures is preferred. 
  • Desired interdisciplinary skills include big data technologies, ETL, statistics and causal inference, Deep Learning, modeling and simulation.
  • Intermediate to advanced ability to create data visualizations using Python.
  • Leading data science projects or teams (as the most technically advanced team member) or working independently on data science projects. 
  • Experience with large data sets and distributed computing (Hive/Hadoop) a plus.
  • Strong skills in software prototyping and engineering with expertise in applicable programming and analytics languages (Python, R, Spark/Scala) and various open source machine learning and analytics packages to generate deliverable modules and prototype demonstrations of their work.








Department: Data Scientist

Equal Employment Opportunity

CareFirst BlueCross BlueShield is an Equal Opportunity (EEO) employer.  It is the policy of the Company to provide equal employment opportunities to all qualified applicants without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, protected veteran or disabled status, or genetic information.

Hire Range Disclaimer

Actual salary will be based on relevant job experience and work history.

Where To Apply

Please visit our website to apply:

Closing Date

Please apply before: 11/01/2019

Federal Disc/Physical Demand

Note:  The incumbent is required to immediately disclose any debarment, exclusion, or other event that makes him/her ineligible to perform work directly or indirectly on Federal health care programs.


The physical demands described here are representative of those that must be met by an employee to perform the essential duties and responsibilities of the position successfully.  Requirements may be modified to accommodate individuals with disabilities.


The employee is primarily seated while performing the duties of the position.  Occasional walking or standing is required.  The hands are regularly used to write, type, key and handle or feel small controls and objects.  The employee must frequently talk and hear.  Weights of up to 25 pounds are occasionally lifted.


Sponsorship in US

Must be eligible to work in the U.S. without Sponsorship

Learn more about Information Technology