Lead AI Data Engineer: Knowledge Graphs on AWS

General Electric; Wilmington (NC); On-site; USD 110,000 - 145,000; Full time

Job summary

GE Aerospace seeks a Senior Data Engineer to design and implement the AWS-native data foundation behind enterprise AI apps, including knowledge graphs, semantic layers, and retrieval pipelines. You will guide design strategy and perform hands-on engineering to implement scalable data systems for grounding, provenance, and explainability.

You will model data, build ingestion pipelines in Python/SQL on AWS, and mentor engineers.

Qualifications

• Bachelor's degree in Computer Science, Engineering, or a STEM field.
• A minimum of three years of data engineering experience.

Responsibilities

• Lead the design and evolution of knowledge graphs and ontologies powering our AI's reasoning, retrieval, and explainability.
• Align enterprise data into a coherent, queryable graph with provenance across sources.
• Own the retrieval substrate — graph queries, vector indexes, and hybrid retrieval — and drive improvements in grounding quality.
• Curate grounding corpora, eval datasets, and retrieval benchmarks for LLM-based features.
• Instrument metrics for retrieval quality, grounding accuracy, and freshness; drive improvements over time.
• Shape training and inference data contracts with AI engineers, including feedback loops from user signals.
• Produce data models for operational/analytical workloads; establish naming conventions and reuse patterns.
• Build ingestion/transformation pipelines in Python/SQL using AWS services (Glue, Lambda, Step Functions, S3, Athena, OpenSearch, Neptune).
• Author infrastructure as code in CloudFormation (CDK welcome) and apply AWS best practices for IAM, security, cost, and observability.
• Profile sources, identify data quality gaps, and design automated validation, monitoring, metadata, and lineage.
• Partner with security/platform teams to integrate data access with identity policies for AI modernization.
• Define data contracts and metadata for policy engines.
• Contribute to the data dictionary, glossary, and data catalog.
• Set design direction for data/semantic modeling and mentor engineers and citizen developers.
• Communicate trade-offs and value to product, business, and executives.

Skills

Knowledge graphs

Data modeling

Python

SQL

AWS proficiency

Communication

Leadership

Cross-functional collaboration

Cypher

Gremlin

SPARQL

OpenSearch

Bedrock

Education

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

Tools

Neo4j

Neptune

TigerGraph

RDF/SPARQL

Cypher

Gremlin

SPARQL

CloudFormation

CDK

Glue

Lambda

Step Functions

S3

OpenSearch

Bedrock

Job description

GE Aerospace seeks a Senior Data Engineer to design and implement the AWS-native data foundation behind enterprise AI apps, including knowledge graphs, semantic layers, and retrieval pipelines. You will guide design strategy and perform hands-on engineering to implement scalable data systems for grounding, provenance, and explainability.

You will model data, build ingestion pipelines in Python/SQL on AWS, and mentor engineers.