GraphDB Engineer

Knowledge Graph Design and Development

Design and build a robust and scalable knowledge graph to represent codification content, product data, and document metadata.

Implement graph structures optimized for search and retrieval of healthcare and insurance-specific content.

Advanced Search Solutions

Develop search algorithms tailored for semantic search and codification lookups.

Evaluate the suitability of GraphDB vs. non-GraphDB solutions for search optimization.

Leverage GraphRag (Graph Retrieval-Augmented Generation) techniques to enhance search and knowledge retrieval capabilities.

Integration with Enterprise Systems

Collaborate with AI/ML teams to integrate predictive and generative models with the knowledge graph.

Ensure seamless integration with existing custom platforms and APIs used within the enterprise.

Performance and Scalability

Design solutions to handle increasing API hits and a growing user base effectively.

Optimize queries, indexing, and data pipelines for high performance under load.

Collaboration and Communication

Work closely with software engineers, developers, and product management teams to align technical solutions with business needs.

Document design decisions, workflows, and best practices clearly and concisely.

Technical Skills

GraphDB Expertise:

Proficiency in Neo4j, Amazon Neptune, or similar graph databases.

Strong knowledge of graph query languages like Cypher, Gremlin, or SPARQL.

GraphRag Implementation:

Experience with or willingness to explore GraphRag to augment search capabilities using graph-based data structures.

Search Algorithm Development:

Expertise in building semantic and contextual search solutions.

Familiarity with NLP techniques for text data processing and retrieval.

Data Integration and Handling:

Hands-on experience with processing diverse data types (eg, product data, codified data, PDF documents).

Knowledge of ETL pipelines and data transformation for graph databases.

Programming and Tools:

Proficiency in Python, Java, or similar languages.

Familiarity with AI/ML frameworks (eg, TensorFlow, PyTorch) for potential integrations.
Soft Skills

Ability to assess and recommend optimal technologies and architectures.

Strong problem-solving and analytical skills.

Effective collaboration and communication with cross-functional teams.

Preferred Qualifications:

Experience in the healthcare or insurance domain.

Familiarity with large-scale distributed systems and scaling strategies for GraphDBs.

Prior experience integrating knowledge graphs with AI/ML models.

Hands-on experience with cloud-based solutions and APIs for graph databases.