Data Scientist II

Wwshemi; Northern (KY); Remote; USD 137,000 - 161,000; Full time

Job summary

Cohere Health, Inc. in Boston, Massachusetts (Remote) seeks a Data Scientist II to translate business needs into data-driven insights. You will gather requirements, perform trend analyses, and analyze healthcare data to identify actionable opportunities.

You will build scalable data pipelines with AWS Airflow, PySpark, and Sagemaker, develop NLP/LLMs, and deliver dashboards and models that support enterprise decisions. Occasional travel to HQ may be required.

Qualifications

• Experience analyzing healthcare datasets (EMR/EHR, medical and pharmacy claims, SDoH).
• Data quality analysis to identify gaps or inconsistencies.
• Build scalable AWS Airflow pipelines to ingest, transform and load terabytes of data using Python, PySpark, and AWS S3; support decision-making in AWS Sagemaker.
• Use regression analysis and outlier detection to identify trends and anomalies in data.
• Develop NLP/LLMs (extractive and generative), fine-tuning and deployment for analytics tasks.
• Develop data models, algorithms, and simulations to support analytical objectives.
• Develop Tableau visualizations and partner with stakeholders to integrate data science into workflows.

Responsibilities

• Gather business requirements and apply trend analysis to identify actionable insights.
• Analyze healthcare data to identify outliers, patterns, and opportunities.
• Train, fine-tune, and implement LLMs and deep learning models for anomaly detection and classification.
• Monitor industry trends and regulatory changes to support strategy and documentation.
• Develop and deploy data models, algorithms, and simulations for analytical objectives.
• Build visualizations and dashboards to communicate findings and support business workflows.

Skills

Python

PySpark

Tableau

NLP

LLMs

Regression analysis

Outlier detection

Data modeling

Dashboards

Tools

AWS Airflow

AWS Sagemaker

SQL

Apache Spark

S3

Job description

Data Scientist II, Cohere Health, Inc., Boston, Massachusetts (Remote)

Duties: Gather business requirements and apply trend analysis to identify actionable insights using analytic tools. Analyze healthcare claims and authorization data to identify outliers, interpret patterns, and assess trends and opportunities. Apply large language models (LLMs), stochastic optimization methods, and related technologies to support decision-making. Monitor industry trends, regulatory changes, and emerging fraud schemes to support detection strategy development, maintain methodology documentation, and present findings to leadership. Train, fine-tune, and implement LLMs and deep learning models for tasks such as anomaly detection, classification, and automated analysis of security-related or operational data. Analyze datasets to assess expected impacts and return on investment, including effects on medical expense, administrative cost, and clinical outcomes. Develop data models, algorithms, and simulations to support analytical objectives. Build visualizations and dashboards to communicate analytical findings and support business workflows.

This is a fully remote position and may be performed from anywhere within the United States. Occasional travel to company headquarters in the U.S. for onboarding, team meetings, and company events may be required.

Requirements:

• Analyzing healthcare datasets, including EMR/EHR data, medical and pharmacy claims data, and Social Determinants of Health (SDoH) data;
• Performing data quality analysis to identify data quality issues, gaps, or inconsistencies;
• Building scalable AWS Airflow pipelines to ingest, integrate, and transform terabytes of data using Python and PySpark and AWS S3 storage, and accelerate business decision-making in AWS Sagemaker;
• Utilizing trend identification and data analysis methods such as regression analysis and outlier detection model in python, spark and sql.;
• Building and implementing models, creating algorithms, and running simulations;
• Developing Tableau visualization and partnering with product owners and stakeholders to drive enterprise-level solutions that integrate data science into business workflows;
• Developing NLP, LLMs (extractive and generative), fine-tuning, and LLM model development.

Salary range is $137,000.00 to $161,000.00 per year for a 40-hour work week.