Kaiser Permanente is seeking a Data Scientist to support scoping, deploying, and reporting out on projects to support prospective risk adjustment projects, identifying and prioritizing prospective risk initiatives, and developing comprehensive reporting and insightful visualization of opportunities and outcomes.
Requirements
- Minimum three (3) years experience working with Exploratory Data Analysis (EDA) and visualization methods.
- Minimum three (3) years machine learning and/or algorithmic experience.
- Minimum three (3) years statistical analysis and modeling experience.
- Minimum three (3) years programming experience.
- Knowledge, Skills, and Abilities (KSAs): Advanced Quantitative Data Modeling; Algorithms; Applied Data Analysis; Data Extraction; Data Visualization Tools; Machine Learning; Relational Database Management; Microsoft Excel; Design Thinking; Business Intelligence Tools; Data Manipulation/Wrangling; Data Ensemble Techniques; Feature Analysis/Engineering; Open Source Languages & Tools; Model Optimization; Strategic Thinking; Deep Learning/Neural Networks; Project Management
- One (1) year experience working with Kubernetes.
- One (1) year experience working with Docker.
Responsibilities
- Develops detailed problem statements outlining hypotheses and their effect on target clients/customers by defining scope, objectives, outcome statements and metrics.
- Designs and develops data pipelines and automation for data acquisition and ingestion of raw data from multiple data sources and data formats by transforming, cleansing, and storing data for consumption by downstream processes; writing and optimizing diverse SQL queries; and demonstrating advanced knowledge of database fundamentals.
- Analyzes and investigates complex data sets and summarizes key characteristics by employing data visualization methods; and determining how best to manipulate data sources to discover patterns, spot anomalies, test hypotheses, and/or check assumptions.
- Selects, manipulates, and transforms data into features used in machine learning algorithms by leveraging techniques to conduct dimensionality reduction, feature importance, and feature selection.
- Trains statistical models by using algorithms and data mining techniques; testing models with various algorithms to assess the input dataset and related features; and applying techniques to prevent overfitting such as cross-validation.
- Deploys and maintains reliable and efficient models through production.
- Verifies model performance by demonstrating expertise in the practice of a variety of model validation techniques to assess and discriminate the goodness of model fit; and leveraging feedback and output to manage and strengthen model performance.
Other
- Bachelors degree in Mathematics, Statistics, Computer Science, Engineering, Economics, Public Health, or related field AND Minimum five (5) years experience in data science or a directly related field.
- Minimum one (1) year experience in a leadership role with or without direct reports.
- Travel: Yes, 5 % of the Time
- Employee Status: Regular
- Job Schedule: Full-time
