Principal Data Scientist - Irvine, CA - 2388090

UnitedHealth Group•Irvine, CA

3d•$226,500 - $315,054•Hybrid

About The Position

Optum Services Inc. is seeking a Principal Data Scientist to join their team in Irvine, CA. This role involves initiating and driving novel method development in machine learning, from conception to deployment. The position requires embedding Artificial Intelligence in Risk Adjustment programs, developing deep learning and statistical learning architectures, and performing statistical inquiries to identify growth areas. The Principal Data Scientist will collaborate with Engineering, Business, and Technical Product teams to deliver technology solutions, mentor junior data scientists, and improve system monitoring. Key responsibilities include identifying new approaches in medical coding, designing and launching novel machine learning methods into production, analyzing trends in medical coding and model performance, directing research in deep learning and LLM approaches, leading research talks, and ensuring models align with ethical standards to prevent user harm. The position reports to the Irvine, CA office and allows for partial telecommuting.

Requirements

Bachelor's degree in Computer Science, Engineering, Information Technology, or related field and seven (7) years of progressive, post-baccalaureate experience in the job offered or in a related computer occupation.
7 years of experience in Machine learning and data science, including data analysis, algorithm design, model architecture specification, and implementation of machine learning algorithms.
7 years of experience in Programming in Python and Java, focused on libraries including PyTorch for deep learning and Pandas for data manipulation and analysis.
7 years of experience in Medicare Advantage Chart Review program contributing to healthcare analytics and compliance-driven data initiatives.
5 years of experience in Big data technologies, including Apache Hadoop, PySpark, Sqoop, Oozie, Hive, and Java-based web services for distributed data processing and workflow orchestration.
5 years of experience in Microsoft Azure, Databricks, including cloud-based data processing, model deployment, and scalable architecture design.
5 years of experience in IBM Business Rule Management System (BRMS) for rule-based automation and enterprise logic management.
5 years of experience in Visualization Tools including Tableau, Seaborn, Matplotlib Libraries.
5 years of experience in Database including SQL, Oracle, HIVE, and HBase.
3 years of experience in Managing data science teams performing deep learning architectures and scalable model development.
3 years of experience in Medicaid and ACA.
3 years of experience in Medicare star rating and quality measures.

Responsibilities

Initiate and drive novel method development in machine learning from first principles to deployed solutions.
Embed Artificial Intelligence in Risk Adjustment prospective and retrospective programs.
Provide innovative modifications and extensions to existing deep learning and statistical learning architectures.
Perform statistical inquiries into new areas and identify growth points of untapped information.
Partner with Engineering, Business and Technical Product teams to meet project commitments by rapidly delivering value to customers via technology solutions.
Mentor junior data scientists to successfully deliver software and business value.
Improve alerts, monitors, and telemetry.
Identify new means of approaching problems in the medical coding field.
Design novel methods in machine learning and launch them to production.
Analyze trends in medical coding and production performance of statistical models.
Direct the research direction of a multidisciplinary team focused on deep learning and LLM approaches.
Lead research talks and white paper reviews.
Conduct research meant to ensure alignment of models to ethical standards to ensure machine learning models perform without harm to users.