GenAI Data Architect: Graph DBs, Vectors & Pipelines

VBeyond Corporation; New York (NY); Vor Ort; USD 150.000 - 190.000; Vollzeit

Zusammenfassung

VBeyond Corporation is seeking an experienced Data Architect in New York to design scalable data architectures and data models that support GenAI applications and AI-driven knowledge platforms. You will lead end-to-end data engineering, from ingestion to enrichment, across structured, semi-structured, and unstructured data.

The role emphasizes graph database design using Neo4j, Python-based data services with FastAPI, and tight integration of relational and vector data stores with governance,

Qualifikationen

• Experience designing scalable data architectures and data models.
• Hands-on development of ETL/ELT pipelines for diverse data.
• Build and optimize graph data models using graph databases.
• Develop Python-based data services and APIs for AI workloads.
• Integrate relational, graph, and vector data stores with accuracy.
• Collaborate with GenAI teams to meet ingestion and retrieval needs.

Aufgaben

• Design scalable data architectures, data models, and ETL/ELT pipelines.
• Build data pipelines to ingest documents and data into AI platforms.
• Develop graph data models using Neo4j or equivalent.
• Develop Python-based data pipelines and services with FastAPI.
• Work with PostgreSQL, pgVector, embeddings, and vector search integrations.
• Implement data quality, lineage, metadata, and reprocessing mechanisms.
• Collaborate with GenAI and AI agent teams to meet data requirements.

Kenntnisse

Data architecture

Data modeling

ETL/ELT pipelines

Graph databases

Python

API development

Vector search / embeddings

GenAI / AI readiness

Tools

Neo4j

PostgreSQL

pgVector

FastAPI

REST APIs

Jobbeschreibung

VBeyond Corporation is seeking an experienced Data Architect in New York to design scalable data architectures and data models that support GenAI applications and AI-driven knowledge platforms. You will lead end-to-end data engineering, from ingestion to enrichment, across structured, semi-structured, and unstructured data.

The role emphasizes graph database design using Neo4j, Python-based data services with FastAPI, and tight integration of relational and vector data stores with governance,