Data Scientist

DESCRIPTION:

Duties: Create data pipelines needed to deliver new analytics products.

Create and deliver custom analyses of payments data's financial cost according to client request.

Design repeatable analytics insights for product development.

Optimize existing data pipelines.

Write and update automated jobs to implement data pipelines.

Measure data quality at all stages of data pipelines.

Design and implement automatic data quality monitoring on all data pipelines.

Adhere to rigorous analytics quality controls in all development and adhoc analysis work.

Create and preserve auditable artifacts for analytics and development work processes.

Meet with clients and stakeholders to elicit requirements for new data insights products.

Maintain business data models needed to support simulation and counterfactual analyses.

Create and update code.

Own and maintain components and subject areas in analytics insights products.

Assess complex interchange costs and optimality applications.

Interpret vendor documentation to develop reference models and applied models of cost and routing decisions.

Meet with internal stakeholders and external clients at all stages of analytics product development.

Independently deliver complex analytics work supporting the needs of the business using statistical methods.

QUALIFICATIONS:

Minimum education and experience required: Master's degree in Information Technology and Management, Data Science, Computer Science, Mathematics, Analytics, Operations Research or related field of study plus 1 year of experience in the job offered or as Data Scientist, Software Developer, or related occupation.

Skills Required: Requires 1 year of experience with the following: Software development life cycle; Software architecture and design; utilizing SQL with big data including performance tuning, query optimization, analytic functions, window functions, CTEs (Common Table Expressions), and recursive queries; translating business requirements and producing technical solutions; interpreting technical specifications and producing analytical data models; using statistics and machine learning to perform hypothesis testing, regression analysis, and time series analysis; applied statistics in SQL or Python.

Requires any amount of experience with the following: Distributed Computing in Hadoop using Hive and Spark; MapReduce; performance tuning and optimization with Snowflake; using machine learning algorithms and frameworks to develop and maintain simulation models for cost optimization, cost modeling, and financial analysis; writing and optimizing Python UDFs for data processing and analysis; deploying and maintaining UDFs in a production environment; utilizing techniques for optimizing the performance of data processing and querying; profiling and debugging performance issues; selection and use of appropriate hypothesis tests; analysis methods including ANOVA, factor analysis, and cluster analysis; linear, logistic and regularized regression; ...