Healthcare Data Scientist & AI Solutions

BioVid; Bristol Township (Bucks County); On-site; USD 120,000 - 160,000; Full time

Job summary

BioVid is transforming pharmaceutical market research by replacing slow, traditional methodologies with AI-augmented data systems.

In this role, you will personally analyze data to uncover HCP prescribing behavior and behavioral insights, bridging quantitative real-world data with qualitative market research while developing synthetic audiences and scalable forecasting, segmentation, and market intelligence solutions.

Qualifications

• Hands-on analysis of medical/pharmacy claims data to extract and predict HCP prescribing behavior.
• Translate analyses into actionable segmentation, targeting, and forecasting insights.
• Tag attitudinal HCP segments to NPIs and link them to prescribing behavior.

Responsibilities

• Data cleaning, gap analysis, joining and data augmentation, transformation to create partitions and analytics workspaces in AWS/Athena.
• Resolve identity matching, tokenization, and data harmonization challenges across disparate sources.
• Build scalable, tested data models using dbt on AWS/Athena.

Skills

HCP data analysis

SQL

Python (pandas)

AWS data pipelines

Tools

dbt

AWS Athena

SageMaker

Great Expectations

Job description

BioVid is transforming pharmaceutical market research by replacing slow, traditional methodologies with AI-augmented data systems.

In this role, you will personally analyze the data to uncover HCP prescribing behavior and behavioral insights. You will help bridge quantitative real-world data with qualitative market research, and play a key role in developing synthetic audiences (“Digital Twins”) that mirror healthcare provider prescribing behavior and patient treatment journeys, while enabling scalable forecasting, segmentation, and market intelligence solutions.

Must-Have Qualifications

Hands-on analysis of medical / pharmacy claims data (EHR preferred)

Direct, hands-on experience analyzing the data itself — not only engineering it. You can extract and predict HCP prescribing behavior for specific drugs, for specific conditions, in specific treatment areas, and tag HCP qualitative / attitudinal segments to NPIs, associating those segments with real prescribing behavior. HIPAA requirements fluent (most of our data will be deidentified)

• Analyze medical and pharmacy claims to extract and predict HCP prescribing behavior for specific drugs, conditions, and treatment areas.
• Perform HCP / patient segmentation, demand forecasting, journey mapping, modeling
• Help build Synthetics, simulated segments and HCP equivalents.
• Machine Learning experience in modeling training and evaluating models (LLM fine tuning, training a nice to have)
• Tag qualitative / attitudinal HCP segments to NPIs and link them to observed prescribing behavior.
• Translate these analyses into actionable segmentation, targeting, and forecasting insights.

Data Cleaning, Processing, Augmentation and Transformation

• Data cleaning, scarcity, gap analysis, joining and data augmentation, transformation to create partitions, data marts and analytics workspaces for analysis and modeling in AWS/Athena.

Key Responsibilities

Data Integration & Modeling

• Data cleaning, scarcity, gap analysis, joining and data augmentation, transformation to create partitions, data marts and analytics workspaces for analysis and modeling inAWS/Athena.
• Resolve identity matching, tokenization, and data harmonization challenges across disparate sources.
• Build scalable, tested, and version-controlled data models using dbt on AWS/Athena.

Data Quality, Governance & Compliance

• Implement automated data quality checks using tools such as Great Expectations or equivalent.

Analytics, AI & Machine Learning

• Conduct advanced exploratory data analysis (EDA) and feature engineering using SQL, Python, pandas, and numpy.
• Analyze claims data to model and predict HCP prescribing behavior by drug, condition, and treatment area, and associate attitudinal segments with NPIs.
• Build AI-powered synthetic provider and patient personas grounded in real-world claims distributions.
• Develop methods to scale qualitative research insights into national quantitative projections.
• Machine Learning experience in modeling training and evaluating models. (LLM fine tuning and training a nice to have
• Perform (or help perform) and automate pharmaceutical market research including:
• HCP segmentation
• Demand forecasting
• Patient journey mapping
• Audience simulation

API & Product Delivery

• Build and maintain performant backend APIs using FastAPI, deployed on AWS (e.g., ECS/Fargate, App Runner, or Lambda).
• Deliver data products, personas, and insights to internal tools and client-facing applications.

Skills & Experience

• 5+ years in Analytics Engineering, Data Engineering, Data Science, or similar roles.
• Proven ownership of end-to-end data pipelines and scalable analytics systems on AWS.
• Hands-on experience with AWS data and analytics tooling, including Athena, S3, Glue, and SageMaker (AWS is the primary environment).
• Strong experience with healthcare claims and EHR data (Rx, Dx, medical, pharmacy) and major data vendors such as IQVIA, Komodo, Symphony, or Definitive Healthcare.
• Demonstrated hands-on analysis of medical/pharmacy claims to extract and predict HCP prescribing behavior and tag attitudinal segments to NPIs.
• Expert SQL and strong Python skills, including pandas and large-scale data workflows.
• Understanding of pharma market research, including patient journeys, HCP segmentation, and demand modeling.
• Experience integrating survey or primary research data with large quantitative datasets.
• Comfortable using AI coding assistants and agentic development tools to accelerate delivery.