Sr. Associate, Data Science

Sr. Associate, Data Science – (job location is Boston, MA; employer is Santander Bank, N.A.) - Perform large-scale data mining and data science projects as well as ad hoc statistical and data mining analyses. Provide analytics support across lifecycle initiatives: deposit portfolio management, CD (certificate of deposit) maturity, money market pricing, etc. Lead analytic projects to support key business strategies and initiatives, and communicate conclusions and result to senior management. Design, deploy, and enhance predictive or behavioral models to address critical business issues, improve automation and overall efficiencies. Research and develop predictive analytics for continuous optimization of business processes using problem sets based on structured and unstructured data. Gather and process data, create hypotheses, test algorithms and scale to large datasets, and provide feedback on patterns and insights based on detailed data analysis. Present results of analyses to business units, and explain technical and statistical concepts to non-technical/non-statistical associates. Develop dashboards and related reports to highlight key performance metrics and trends. Requirements: Master’s degree in Applied Mathematics, Statistics, or Data Science, plus 2 years of experience in the position offered or as Data Engineer or Data Scientist. All required experience must have included conducting predictive analytics to predict business trends and provide forecasts that drive business decisions and business planning; preparing and justifying business cases and value propositions based on cost, benefits, ROI, opportunities, and risks; summarizing, simplifying and effectively explaining complex technical concepts to stakeholders; designing and optimizing data pipelines, data modeling, ETL processes, data warehousing and data governance; extracting patterns and information from terabyte to petabyte scale data and turning them into interpretable structure for business using big data tools including Presto, Spark, Hadoop, Hive, and Kafka; performing statistical analysis and measurement using A/B testing, linear and non-linear regression, logistic regression, clustering (k-means, EM, Mean-shift), classification algorithms, decision trees, ensembles (bagging, boosting, rand), deep learning models, and NLP; and using Python (Numpy, Pandas, Matplotlib, Scipy, Scikit-Learn, and PyTorch), SQL, Presto, Spark, Hive, R, Tableau, SAS, Git, JIRA, Confluence and Excel. #LI-DNI This role entails hybrid work, with time split between working in our Boston, MA office and flexibility to telecommute from another U.S. location. E-mail résumé to: dsebock@santanderconsumerusa.com. Ref. #54.