Analytic Science-Scientist II Job at FICO

FICO is hiring for the role of Analytic Science-Scientist II!

Responsibilities of the Candidate:

• Build features that enhance and empower consumer understanding of the FICO Score.
• Designs and develops state-of-the-art, data-driven exploratory analysis as well as predictive and decision models to solve business problems.
• This includes the analysis of large amounts of historical data, determining suitability for modeling, data clean-up, pattern identification and variable creation, selection of sampling criteria and performance definition, and variable selection.
• Assists with technical product support for new or existing products/services; this includes, but is not limited to, production of sales collateral or ad-hoc investigations initiated by internal or external clients.
• May deliver formal presentations of work to clients

Requirements:

• Bachelor’s Degree in Computer Science, Cognitive Science, Engineering, Physics, Statistics, Mathematics, Operations Research or other Natural Science Field.
• Experience working with U.S. Credit Bureau data (Highly Preferred).
• Experience building B2C-facing analytic solutions (Highly Preferred).
• Hands-on related experience in predictive modeling and data mining. 
• Related experience (school or industry) in predictive modeling and data mining is preferred.
• Experience with one or more of R, Python, SAS, SQL, and Java/C++, experience with tools for machine learning and unstructured data analysis (e.g., H2O, Splunk, TensorFlow, etc.) and familiarity with basic software design principles and coding standards and best practices.
• Experience with distributed computing environments (e.g., Spark, Hadoop) and cloud-based environments and services (e.g., AWS) would be a plus.
• Experience analyzing large datasets and applying data-cleaning techniques along with performing statistical analyses leading to the understanding of the structure of datasets.
• Prefer knowledge in some of the following: clustering, classification and regression trees, random forest and gradient boosting algorithms, time series analysis, Bayesian networks, PCA, independent component analysis, linear and logistic regressions, inference, estimation, experimental design, neural networks, SVM