Data Scientist III

Kaiser Permanente; Oakland (CA); Sur place; USD 120 000 - 170 000; Plein temps

Résumé du poste

Kaiser Permanente seeks a Data Scientist III to develop and apply advanced analytics, ML, and automation to improve risk adjustment data quality and throughput.

You will work with Python, SQL, Databricks, and ML techniques to transform data into actionable insights, build predictive models, and deploy them into production. Collaboration with stakeholders across domains is essential.

Qualifications

• Minimum two (2) years experience working with Exploratory Data Analysis (EDA) and visualization methods.
• Minimum one (1) year machine learning and/or algorithmic experience.
• Minimum two (2) years statistical analysis and modeling experience.
• Minimum two (2) years programming experience.
• Bachelor’s degree requirement as listed under Education.

Responsabilités

• Pursues effective relationships with others by proactively providing resources, information, advice, and expertise with coworkers and members. Listens to, seeks, and addresses performance feedback; provides mentoring to team members.
• Completes work assignments autonomously by applying up-to-date expertise in subject area to generate creative solutions; ensures all procedures and policies are followed; leverages an understanding of data and resources to support projects or initiatives.
• Develops detailed problem statements outlining hypotheses and their effect on target clients/customers by defining scope, objectives, outcome statements and metrics.
• Participates in the design and development of data pipelines and automation for data acquisition and ingestion of raw data from multiple data sources and data formats under the guidance of more senior data scientists by transforming, cleansing, and storing data for consumption by downstream processes; writing and optimizing diverse SQL queries; and demonstrating a working knowledge of database fundamentals.
• Analyzes and investigates 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 under the guidance of more senior data scientists 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 a working knowledge 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.
• Works with internal and external stakeholders across domains to develop and deliver statistical driven outcomes by delivering insights and values from heterogeneous data to investigate problems for multiple use cases; driving informed decision-making; and presenting findings to both technical and non-technical audiences.

Connaissances

Ambiguity, uncertainty management

Attention to detail

Communication

Critical thinking

Cross-group collaboration

Problem solving

Teamwork

Topic-specific communication

Learning agility

Formation

Bachelor's degree in Mathematics, Statistics, Computer Science, Engineering, Economics, Public Health, or related field

Outils

Microsoft Excel

Open Source Languages & Tools

Description du poste

The Risk Adjustment Data Management and Integrity team provides Medicare Advantage, Medicaid, and ACA risk-related data to support key business initiatives. The ideal candidate has strong SQL and data transformation skills, experience managing large datasets, and a background in healthcare analytics or risk adjustment. Success in this role requires strong quality assurance, communication, collaboration, and problem-solving skills.

The Data Scientist III develops and applies advanced analytics, machine learning, and automation to improve risk adjustment data quality, throughput, and operational effectiveness. This role analyzes complex healthcare datasets, identifies data integrity issues and remediation opportunities, and develops predictive models and automated solutions to enhance the accuracy and completeness of risk adjustment submissions. Leveraging Python, SQL, Databricks, and machine learning technologies, the Data Scientist III helps drive the transition from rules-based analysis to predictive, intelligence-driven decision-making. The ideal candidate has experience with healthcare and risk adjustment data, predictive modeling, anomaly detection, and process optimization, along with strong analytical, communication, and cross-functional collaboration skills.

Job Summary:

This individual contributor is primarily responsible for participating in the design and development of data pipelines and automation for data acquisition and ingestion of raw data from multiple data sources and data formats under the guidance of more senior data scientists. This role is also responsible for developing detailed problem statements outlining hypotheses and their effect on target clients/customers, analyzing and investigating data sets and summarizing key characteristics, selecting, manipulating and transforming data into features used in machine learning algorithms, training statistical models under the guidance of more senior data scientists, deploying and maintaining reliable and efficient models through production, verifying model performance, and working with internal and external stakeholders across domains to develop and deliver statistical driven outcomes.

Essential Responsibilities:

• Pursues effective relationships with others by proactively providing resources, information, advice, and expertise with coworkers and members. Listens to, seeks, and addresses performance feedback; provides mentoring to team members. Pursues self-development; creates plans and takes action to capitalize on strengths and develop weaknesses; influences others through technical explanations and examples. Adapts to and learns from change, challenges, and feedback; demonstrates flexibility in approaches to work; helps others adapt to new tasks and processes. Supports and responds to the needs of others to support a business outcome.
• Completes work assignments autonomously by applying up-to-date expertise in subject area to generate creative solutions; ensures all procedures and policies are followed; leverages an understanding of data and resources to support projects or initiatives. Collaborates cross-functionally to solve business problems; escalates issues or risks as appropriate; communicates progress and information. Supports, identifies, and monitors priorities, deadlines, and expectations. Identifies, speaks up, and implements ways to address improvement opportunities for team.
• Develops detailed problem statements outlining hypotheses and their effect on target clients/customers by defining scope, objectives, outcome statements and metrics.
• Participates in the design and development of data pipelines and automation for data acquisition and ingestion of raw data from multiple data sources and data formats under the guidance of more senior data scientists by transforming, cleansing, and storing data for consumption by downstream processes; writing and optimizing diverse SQL queries; and demonstrating a working knowledge of database fundamentals.
• Analyzes and investigates 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 under the guidance of more senior data scientists 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 a working knowledge 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.
• Works with internal and external stakeholders across domains to develop and deliver statistical driven outcomes by delivering insights and values from heterogeneous data to investigate problems for multiple use cases; driving informed decision-making; and presenting findings to both technical and non-technical audiences.

Knowledge, Skills and Abilities: (Core)

• Ambiguity/Uncertainty Management
• Attention to Detail
• Business Knowledge
• Communication
• Critical Thinking
• Cross-Group Collaboration
• Decision Making
• Dependability
• Diversity, Equity, and Inclusion Support
• Drives Results
• Facilitation Skills
• Health Care Industry
• Influencing Others
• Integrity
• Learning Agility
• Organizational Savvy
• Problem Solving
• Short- and Long-term Learning & Recall
• Teamwork
• Topic-Specific Communication

Knowledge, Skills and Abilities: (Functional)

• Advanced Quantitative Data Modeling
• Algorithms
• Applied Data Analysis
• Business Intelligence Tools
• Data Ensemble Techniques
• Data Extraction
• Data Manipulation/Wrangling
• Data Visualization Tools
• Design Thinking
• Feature Analysis/Engineering
• Machine Learning
• Microsoft Excel
• Model Optimization
• Open Source Languages & Tools
• Relational Database Management

Minimum Qualifications:

• Minimum two (2) years experience working with Exploratory Data Analysis (EDA) and visualization methods.
• Minimum one (1) year machine learning and/or algorithmic experience.
• Minimum two (2) years statistical analysis and modeling experience.
• Minimum two (2) years programming experience.
• Bachelors degree in Mathematics, Statistics, Computer Science, Engineering, Economics, Public Health, or related field AND Minimum three (3) years experience in data science or a directly related field. Additional equivalent work experience in a directly related field may be substituted for the degree requirement. Advanced degrees may be substituted for the work experience requirements.

Preferred Qualifications:

• One (1) year experience in a leadership role with or without direct reports.
• One (1) year healthcare experience.