This position is located in Cincinnati or San Diego. Candidates in other United States locations may be considered.

Position Summary

The Data Scientist responsibility is to develop, enhance, and implement machine learning models and data methodologies for Claritas proprietary solutions in campaign measurement/optimization, predictive models for audience deliver and Data Lake quality assurance. The Data Scientist is the Subject Matter Expert and will collaborate with a team of other skilled and experienced Data Scientists, Data Engineers, and Analysts to create quality data products and deliver useful insights for Claritas clients.

Primary Responsibilities

• Develop and implement predictive models and machine learning algorithms to build scalable, efficient, and automated data solutions
• Support new product ideas by translating them into well-posed data science problems and solving them
• Participate in methodological projects: plan, manipulate, analyze, and interpret large data sources; develop, validate, implement models; tell a story from data through analyses
• Understand and reconcile disparate data sources to make stronger products. Primary areas include, but not limited to, coverage, sampling/representation, bias reduction, indirect estimation, and data integration
• Program in Python, Spark and SQL to wrangle data and conduct R&D
• Create technical and client-friendly methodology documentation
• Collaborate with cross functional teams to design and implement client solutions
• Investigate, troubleshoot, and support client data inquiries
• Participate in the broader statistical and machine learning community to stay current with the latest techniques and software

Skills, Education and Experience

Required:

• Bachelor’s degree in Statistics, Social Science, Computer Science or related quantitative field with minimum of 1-2 years of experience
• Knowledge of data design and analysis, inclusive of data pre-processing, cleaning, editing, model building and analysis
• Strong technical proficiency in Python, experience in Spark is a plus
• Experience and working knowledge of relational and large scale databases and SQL
• Strong applied statistical experience and quantitative analysis in applied marketing and/or consumer insights settings
• Curiosity and skepticism: independently challenge and prove data and methods are fit for purpose
• Creativity and persistence: identify and apply techniques for bias reduction, feature engineering, and data integration; advocate for, and be a guardian of, data quality
• Disposition to simplify: streamline work processes, simply communicate complex statistical concepts
• Excellent verbal and written communication skills
• Excellent problem-solving skills
• Desire to work in a team environment
• Excellent organizational skills with high degree of attention to detail
• Excellent ability to manage multiple projects and meet deadlines

Highly preferred:

• Master’s degree in Statistics, Social Science, Computer Science or related field with a minimum of 1-3 years of experience
• Experience working with cloud-based or big data technologies
• Experience and working knowledge of relationship and large-scale databases and SQL
• Experience with visualization tools