Remote Senior AI Data Engineer - Graphs & Pipelines

GE Aerospace; Auburn (ME); On-site; USD 110,000 - 145,000; Full time

Job summary

GE Aerospace seeks a Senior Data Engineer to design and build the AWS-native data foundation behind our enterprise AI applications, including knowledge graphs, semantic layers, and retrieval pipelines. You will set patterns for data access, curation, and provenance across multiple sources.

You will lead data quality for AI features, define data contracts with AI engineers, and implement pipelines using AWS Glue, Lambda, S3, Athena, OpenSearch, Neptune, and Bedrock services.

Qualifications

• Bachelor's degree in Computer Science, Engineering, or STEM field.
• At least 3 years of data engineering experience.
• Strong AWS proficiency including CloudFormation/CDK, Glue, Lambda, S3, and IAM.
• Experience with knowledge graphs, ontologies, and graph query languages.
• Experience with AI/ML data for LLMs, RAG, embeddings.
• Ability to collaborate cross-functionally and present to non-data audiences.
• Eligibility to work in the U.S. without visa sponsorship.

Responsibilities

• Design and evolve knowledge graphs and ontologies powering AI reasoning, retrieval, and explainability.
• Align data sources into a coherent graph with provenance across sources.
• Own the retrieval substrate: graph queries, vector indexes, and hybrid retrieval; improve grounding quality.
• Curate grounding corpora, eval datasets, and benchmarks for LLM features.
• Instrument metrics for retrieval quality and grounding accuracy; drive improvements.
• Shape data contracts for training and inference with AI engineers.

Skills

Knowledge graphs

AWS

Python

SQL

Data modeling

Data governance

Leadership

Education

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

Tools

OpenSearch

Neptune

Bedrock

CloudFormation/CDK

S3

Glue

Lambda

Step Functions

Athena

Neo4j

Job description

GE Aerospace seeks a Senior Data Engineer to design and build the AWS-native data foundation behind our enterprise AI applications, including knowledge graphs, semantic layers, and retrieval pipelines. You will set patterns for data access, curation, and provenance across multiple sources.

You will lead data quality for AI features, define data contracts with AI engineers, and implement pipelines using AWS Glue, Lambda, S3, Athena, OpenSearch, Neptune, and Bedrock services.