As part of the AI Health team, utilize expertise in machine learning techniques such as decision trees, neural networks, graphical models, and LLM fine-tuning to design and build predictive models that address critical healthcare questions. Employ clustering, dimension reduction, and deep generative models to uncover patterns and insights within complex healthcare data. Validate and deploy models, ensuring their accuracy, reliability, and ethical use. Collaborate with data engineers to design and implement robust pipelines that streamline data processing, cleaning, and feature extraction. Analyze and interpret raw data using statistical methods and data visualization tools to uncover insights and guide decision-making processes within the program. Leverage statistical and domain expertise to engineer meaningful features that improve model performance and drive actionable insights. Ensure data quality, consistency, and security throughout the model development lifecycle. Partner with clinicians, researchers, product managers, and software engineers to translate healthcare challenges into data science problems. Communicate complex technical concepts to diverse stakeholders, empowering them to make informed, data-driven decisions. Provide thought leadership and guidance to the team, acting as a subject matter expert in data science and machine learning. Experiment with new approaches and technologies to enhance model performance and expand the organization's data science capabilities. Position allows for 100% remote work.

REQUIREMENTS: Bachelor's degree, or foreign equivalent, in Bachelor's degree, or foreign equivalent, in Business Analytics, Computer Science, Engineering (any), or a related field. -Two (2) years of experience using statistical analysis to monitor pilots and developments with ML models to measure program impact;

-Two (2) years of experience creating visualizations (including, matplotlib, seaborn, and plotly) to summarize and communicate model performance metrics, statistical analysis outcomes, and experiment results to technical and non-technical stakeholders.

-Two (2) years of experience training and deploying machine learning models;

-Two (2) years of experience coding in Python; and

-Two (2) years of experience manipulating data to prepare source data for training machine learning models using SQL and PySpark.

Experience can be gained through work experience or graduate-level coursework. Position allows for 100% remote work.

To apply, email resume to dslocum@geisinger.edu using job code: AMB

Geisinger System Services jobs

AI Data Scientist Intermediate