Staff Data Scientist - Scalable ML Pipelines for Healthcare

Vi; Boston (MA); On-site; USD 140,000 - 220,000; Full time

Job summary

Vi Engage is seeking a senior data scientist to own scalable ML pipelines training, scoring, and deployment across health system deployments. You will turn longitudinal data into predictive models that generalize across customers with automated feature engineering and model selection.

Role emphasizes production quality, end-to-end pipeline building in Python stack (pandas, sklearn, PySpark, Airflow) and cloud tooling (AWS/SageMaker). On-site Boston preferred.

Qualifications

• Shipped uplift or propensity models in production that changed business outcomes.
• POC to product: repeatable deployments across multiple customers.
• Deep data science: segmentation, campaign optimization, uplift estimation.
• Proficient in Python stack and end-to-end pipeline construction.

Responsibilities

• Develop and maintain scalable ML pipelines that train, score, and deliver predictions.
• Implement automatic feature engineering and model selection for customer deployments.
• Improve cross-customer generalization across workloads.
• Productize pilots into durable capabilities for future deployments.

Skills

Python

ML engineering

Pandas

PySpark

Airflow

SageMaker

Tools

SageMaker

PySpark

Airflow

Pandas

SQL

Job description

Vi Engage is seeking a senior data scientist to own scalable ML pipelines training, scoring, and deployment across health system deployments. You will turn longitudinal data into predictive models that generalize across customers with automated feature engineering and model selection.

Role emphasizes production quality, end-to-end pipeline building in Python stack (pandas, sklearn, PySpark, Airflow) and cloud tooling (AWS/SageMaker). On-site Boston preferred.