AI Data Engineer – RAG Pipelines & Production

Greenkey Resources LLC; Washington; Hybrid; USD 140,000 - 190,000; Full time

Job summary

Greenkey Resources LLC is seeking an experienced Engineer to transform data and AI architecture into production systems. You will design AI-ready data pipelines, implement RAG components, and build semantic models to ground analytics.

The role requires collaboration across federated data models and regulated environments with a hybrid work setup. You will mentor junior engineers, maintain ETL/ELT pipelines, and ensure data quality and observability while partnering with governance teams to

Qualifications

• Bachelor's degree in computer science, data engineering, or related field.
• 6+ years of technical experience, including 1–2 years in AI/ML systems production.
• Proficiency in Python, SQL, and distributed processing frameworks.
• Experience with modern data stacks such as dbt, Fivetran, and Snowflake.
• Hands-on expertise with AI platforms and tools like AWS Bedrock and OpenAI APIs.
• Knowledge of retrieval-augmented generation pipelines and vector databases.
• Strong engineering craft with a focus on clean code and automated testing.
• Ability to operate in federated data models and regulated enterprise environments.

Responsibilities

• Develop AI-ready data pipelines, embedding generation, indexing, and refresh workflows.
• Implement retrieval-augmented generation components and vector store integrations.
• Maintain interfaces for agents and copilots to query enterprise data safely.
• Design and maintain ELT, streaming, and transformation pipelines using modern tools.
• Build semantic models and analytical/dimensional models for AI grounding.
• Implement data quality checks, lineage capture, and pipeline observability.
• Collaborate with governance teams to ensure rigorous data consumption standards.
• Mentor junior engineers and contribute to architectural design reviews.

Skills

Python

SQL

AI/ML systems production

Data pipelines

Federated data models

RAG patterns

Vector databases

Automated testing

Education

Bachelor's degree in computer science or related field

Tools

dbt

Fivetran

Snowflake

AWS Bedrock

OpenAI APIs

Vector stores

Job description

Greenkey Resources LLC is seeking an experienced Engineer to transform data and AI architecture into production systems. You will design AI-ready data pipelines, implement RAG components, and build semantic models to ground analytics.

The role requires collaboration across federated data models and regulated environments with a hybrid work setup. You will mentor junior engineers, maintain ETL/ELT pipelines, and ensure data quality and observability while partnering with governance teams to