Staff Data Scientist - Scalable Healthcare ML Pipelines

Getvi; Boston (MA); On-site; USD 180,000 - 240,000; Full time

Job summary

Getvi is seeking an applied data scientist/ML engineer to own end-to-end predictive modeling pipelines using longitudinal data from health systems. You will deploy models that identify patients at risk and enable proactive care programs.

In this role, you will scale config-driven pipelines, ensure cross-customer generalization, and work with the cloud stack (AWS) to ship reusable components. Healthcare domain knowledge is a plus.

Qualifications

• Proven track record shipping uplift, survival, or propensity models that changed spending or reach.
• Turn pilots or proofs of concept into repeatable production deployments across customers.
• Fluent Python with pandas, sklearn, PySpark and Airflow.
• Experience with MLOps, model tracking and deployment tooling.

Responsibilities

• Own ML pipelines from data to deployed predictions at scale.
• Build config-driven, reusable components for multiple customers in AWS.
• Defend modeling choices to analytics stakeholders and justify simpler approaches when needed.
• Collaborate with engineers to create internal platforms used by other teams.

Skills

Python

ML Engineering

Pandas

Scikit-learn

PySpark

Airflow

MLflow

SageMaker

Tools

AWS S3

AWS Glue

AWS EMR

AWS MWAA

SageMaker

Job description

Getvi is seeking an applied data scientist/ML engineer to own end-to-end predictive modeling pipelines using longitudinal data from health systems. You will deploy models that identify patients at risk and enable proactive care programs.

In this role, you will scale config-driven pipelines, ensure cross-customer generalization, and work with the cloud stack (AWS) to ship reusable components. Healthcare domain knowledge is a plus.