Highmark Health

Lead Data Scientist – Research and Development, Graph Intelligence

Highmark Health

full-time

Posted on:

Origin:  • 🇺🇸 United States • Louisiana, North Carolina

Visit company website
✨ AI Apply
Manual Apply

Salary

💰 $108,000 - $201,800 per year

Job Level

Senior

Tech Stack

ApacheAWSAzureBigQueryCloudGoogle Cloud PlatformNeo4jNode.jsPythonPyTorchSparkSQL

About the role

  • Work directly with the business to understand processes and aims, then identify analytical solutions; outline complex new use cases and impact estimates
  • Assemble data sets using Highmark operational and analytic data structures; deliver analytical solutions to multiple complex business problems
  • Select and apply appropriate advanced modeling techniques; ensure final analysis is well researched, accurate, and documented
  • Translate results into actionable business insights via written reports, presentations, and data visualizations; link results to business objectives
  • Plan, prepare and deliver analyses largely independently on time and production-ready; determine best route to deployment
  • Lead major projects within ED&A; mentor/teach others; engage with external collaborations
  • Publish seminal findings; contribute to graph intelligence leadership in healthcare

Requirements

  • Required: Master's degree in Analytics, Mathematics, Physics, Computer and Information Science, Engineering Technology or related field OR Bachelor's Degree + 3 years of relevant work experience in lieu of a Master's Degree
  • Preferred Doctoral degree (Ph.D.) in Analytics, Mathematics, Physics, Computer and Information Science, Engineering Technology, or a related field
  • 5 years of Data Science experience
  • 3 years Data Science experience (if PhD Education)
  • Deep Expertise in Graph Theory & Network Science: Centrality, community detection, pathfinding, clustering; knowledge graph principles; network analysis techniques
  • Advanced Graph Machine Learning (GML): Graph Neural Networks (GNNs), graph convolutional networks (GCNs), graph attention networks (GATs) for node classification, link prediction, anomaly detection
  • Knowledge Graph Engineering: schema design (ontologies, RDF, OWL), data ingestion, graph construction, data cleaning, entity resolution, advanced graph querying (Cypher, SPARQL)
  • Graph Database & Platform Experience: Neo4j, Google Spanner Graph, etc.
  • GML Libraries & Frameworks: PyTorch Geometric (PyG), Deep Graph Library (DGL), Spektral, StellarGraph
  • Cloud Platform & MLOps: AWS, Azure, GCP; MLOps for research pipelines
  • Research & Publication Acumen: peer-reviewed publications or demonstrated research experience
  • Healthcare Data Familiarity: healthcare data domains (claims, clinical, EMR) and related ontologies/standards (SNOMED CT, ICD)
  • Experimental Design & Rigor: robust experiments; interpret results; contribute to scientific understanding
  • Travel: 0-25%