AI Data Pipeline Engineer

Bespoke Technologies, Inc.; Reston (VA); On-site; USD 150,000 - 230,000; Full time

Job summary

Bespoke Technologies, Inc. in Reston, VA is seeking a Senior Principal AI Data Pipeline Engineer to lead design and implementation of scalable data pipelines for geospatial data, metadata enrichment, and data cataloging.

You will drive AI-powered data extraction, normalization, and discovery using advanced reader design and adaptable readers. You will leverage AI/LLMs, RAG, MCP, and Node.js dashboards connected to Oracle databases to orchestrate data extraction, enrichment, and ingestion across

Qualifications

• Experience with geospatial data types (rasters and vectors).
• Experience building data pipelines to integrate data from multiple sources.
• Designing and implementing readers to extract metadata from data sources, with a focus on flexible readers that can adapt to new and changing data formats.
• Designing and implementing metadata enrichment capabilities, such as data providence, pedigree, lineage, and security attributes.
• Designing and implementing event pipelines that orchestrate data cataloging processes for different data types, including processes for data extraction, normalization, enrichment, and ingestion.
• Leveraging AI to enhance data extract, enrichment, catalog, and discovery capabilities
• Experience with designing and building AI agents
• Integrating mission data with LLMs using RAG and MCP
• Designing and building Node.js applications and dashboards connected to Oracle Databases
• OpenAI Codex

Skills

geospatial data types

data pipelines

metadata enrichment

event pipelines

AI for data extract/enrichment/catalog

AI agents

RAG and MCP integration

Node.js dashboards

OpenAI Codex

readers for metadata extraction

Tools

Node.js

Oracle Databases

OpenAI Codex

Job description

BT-326 - AI Data Pipeline Engineer

Skill Level- Senior Principal

Location- Reston, VA

Required Skills/Capabilities

• Experience working with geospatial data types (rasters and vectors)
• Experience building data pipelines to integrate data from multiple sources:
• Designing and implementing readers to extract metadata from data sources, with a focus on flexible readers that can adapt to new and changing data formats.
• Designing and implementing metadata enrichment capabilities, such as data providence, pedigree, lineage, and security attributes.
• Designing and implementing event pipelines that orchestrate data cataloging processes for different data types, including processes for data extraction, normalization, enrichment, and ingestion.
• Leveraging AI to enhance data extract, enrichment, catalog, and discovery capabilities
• Experience with designing and building AI agents
• Integrating mission data with LLMs using RAG and MCP
• Designing and building Node.js applications and dashboards connected to Oracle Databases
• OpenAI Codex

Desired Skills/Capabilities

• Oracle Cloud Infrastructure (OCI)
• Oracle AI Database 26ai
• Oracle Exadata and/or OCI Autonomous AI Database Service on Exadata
• AI-enabling data in Oracle Databases using Vector data type, RAG, and MCP
• Designing multi-modal databases that integrate multiple data types, including:
• Relational
• Spatial
• JSON (including JSON Relational Duality)
• Graph