Responsible for developing technical solutions to increase revenue and margin by utilizing Predictive Modeling, Segmentation, and Machine Learning methods. Provides thought leadership for advanced analytic projects and solutions. Works on data science projects from inception to delivery, working with senior leaders and business partners (Technology, Clinical, Operations, etc.) to develop new Predictive, Forecasting, and Natural Language Processing (NLP) models. Performs data mining by applying machine learning and supervised learning algorithms. Supports advanced analytical and data mining efforts including clustering, segmentation, logistic and multivariate regression, decision trees, neural networks, time-series analysis, sentiment analysis, topic modeling, and Bayesian analysis. Visualizes, interprets, reports, and communicates data findings in various formats. Partial virtual/work from home benefit available.
Requires a Master’s degree in any STEM (science, technology, engineering, or math) field plus 2 years of data science experience. Must have experience with: extracting and processing data using SQL and PySpark; developing data models using Python and TensorFlow; deploying data models to production using Amazon SageMaker; developing machine learning models like regression, classification, tree-based, forest-based, and boosting using Python, PySpark, and SQL Programming; developing Deep Learning models like Long Short-Term Memory, Recurrent Neural Network, and Convolution Neural Network using TensorFlow in Python; cross-validation, regularization, dropouts, data augmentation, and early stopping; hyperparameter tuning; Pearson Correlation and Kendall Correlation; parametric tests such as T-test, Z-test, and ANOVA; and non-parametric tests such as Chi-Square and Mann-Whitney U-tests.
*****
Please send us your resume via email at candidates(at) (link removed) with reference #0251200 in the subject line. Do not copy and paste your resume in the body email. Please attach it as a Word document. Thank you.