Senior AI Data Engineer - Remote Graph Pipelines

GE Aerospace; Providence (RI); Remote; USD 110,000 - 145,000; Full time

Benefits offered by this job

Health benefits

401(k) matching

Tuition assistance

Paid time off

Job summary

GE Aerospace is seeking a Senior Data Engineer to design and implement an AWS-based data foundation for enterprise AI applications, including knowledge graphs, semantic layers, and retrieval pipelines. You will shape how our AI systems understand enterprise data and lead hands-on engineering to realize these patterns.

You will mentor others, partner with security and platform teams, and drive data contracts, quality metrics, and governance across structured, semi-structured, and unstructured

Qualifications

• Bachelor's degree in Computer Science, Engineering, or a STEM field.
• Minimum of three years of data engineering experience.
• Proficient in data modeling, graph concepts, and retrieval pipelines.

Responsibilities

• Lead design and evolution of knowledge graphs and ontologies powering AI reasoning and retrieval.
• Align data sources into a coherent, queryable graph with provenance across sources.
• Own retrieval substrate and drive improvements in grounding quality.
• Curate grounding corpora and eval datasets for LLM features.
• Define data contracts and metadata for policy engines and governance.

Skills

Knowledge graphs

Data modeling

Python

SQL

AWS

OpenSearch

Neptune

RAG pipelines

IAM security

Education

Bachelor's degree in Computer Science, Engineering, or STEM

Tools

CloudFormation

CDK

AWS Glue

AWS Lambda

S3

Athena

Job description

GE Aerospace is seeking a Senior Data Engineer to design and implement an AWS-based data foundation for enterprise AI applications, including knowledge graphs, semantic layers, and retrieval pipelines. You will shape how our AI systems understand enterprise data and lead hands-on engineering to realize these patterns.

You will mentor others, partner with security and platform teams, and drive data contracts, quality metrics, and governance across structured, semi-structured, and unstructured