AI-Ready Data Engineer: Pipelines, Governance & Retrieval

GEI Consultants, Inc; Atlanta (GA); Hybrid; USD 90,000 - 150,000; Full time

Benefits offered by this job

Hybrid work schedules

Medical, Dental, Vision

Tuition reimbursement

Profit sharing

Paid time off

Job summary

GEI Consultants, Inc. is seeking a Data Engineer to design, build, and maintain data pipelines powering AI solutions and digital initiatives.

You will prepare data foundations, ingest data, and support retrieval patterns like RAG, collaborating with AI engineers and platform teams to ensure secure, production-ready data infrastructure. Responsibilities include data ingestion, integrations across sources, data modeling, and maintaining governance controls.

Qualifications

• 4+ years of data engineering experience building and operating production data pipelines.
• Proficiency in Python and SQL; PySpark experience preferred.
• Experience with Azure data services (ADF, Synapse, Data Lake Storage, SQL).
• Familiarity with Azure AI Search, Cosmos DB, and AI storage patterns.
• ETL/ELT pipelines across structured, semi-structured, and unstructured data.
• Data modeling, schema design, and indexing for analytical and AI workloads.
• IaC and CI/CD practices (Terraform, Azure DevOps).
• Knowledge of data governance incl. cataloging, lineage, access control, and privacy.

Responsibilities

• Design, build, and maintain data pipelines ingesting and delivering enterprise data to AI solutions.
• Develop and manage integrations across data sources using APIs, Graph connectors, and batch/streaming patterns.
• Build and maintain data stores and indexing for RAG and AI consumption patterns.
• Implement data quality, validation, and lineage controls for data fed to AI workflows.
• Support data models underpinning Power BI dashboards and AI analytics.
• Collaborate with AI Engineers to ensure data contracts meet schema, latency, and freshness needs.
• Instrument pipelines for monitoring, cost control, and performance optimization.
• Implement data governance and security controls including access management and encryption.

Skills

Python

SQL

PySpark

Azure Data Factory

Azure Synapse Analytics

Azure Data Lake Storage

Azure SQL

Azure AI Search

Cosmos DB

ETL/ELT

Data modeling

CI/CD

Terraform

Azure DevOps

Data governance

Security best practices

Databricks

Unity Catalog

Power BI

Tools

Databricks

Power BI

Terraform

Azure DevOps

Job description

GEI Consultants, Inc. is seeking a Data Engineer to design, build, and maintain data pipelines powering AI solutions and digital initiatives.

You will prepare data foundations, ingest data, and support retrieval patterns like RAG, collaborating with AI engineers and platform teams to ensure secure, production-ready data infrastructure. Responsibilities include data ingestion, integrations across sources, data modeling, and maintaining governance controls.