GenAI Data Platform Engineer - AWS & LLM Pipelines

Banner Quality Management Inc; Cleveland (OH); On-site; USD 110,000 - 170,000; Full time

Job summary

Banner Quality Management Inc. seeks an AI Software Developer/Engineer to design, build, deploy, and operate GenAI-enabled data platform capabilities for SMA use cases. The role focuses on AWS-centric data lake architecture, end-to-end data pipelines, and secure APIs for AI workflows.

You will work within a skilled team to implement secure data access, governance, and grounded, source-cited AI outputs, aligning with federal guidelines and enterprise security. Cleveland-based, full-time position.

Qualifications

• 3+ years of hands-on experience building and deploying AI and data-intensive systems in production.
• Proficiency in Python and strong SQL; experience with modern data engineering libraries and frameworks.
• Hands-on AWS experience across storage, compute, data, and AI services, including IAM and security best practices.

Responsibilities

• Architect, build, and operate a cloud data lake on AWS ingesting structured, semi-structured, and unstructured data.
• Design end-to-end data pipelines: ingestion, transformation, embedding generation, and loading into vector/semantic stores.
• Develop and operationalize retrieval-augmented generation (RAG) and agentic GenAI capabilities.
• Design, secure, and document APIs and MCP servers exposing data to LLM orchestrators and applications.
• Implement authentication/authorization using OIDC/OAuth 2.0 and enterprise identity providers.
• Embed data governance: data classification, access controls, PII handling, and audit logging.

Skills

Python

SQL

AWS

Data pipelines

API design

Education

Bachelor's or Master's degree in Computer Science, Data Science, AI, Engineering

PhD preferred for senior levels

Tools

Docker

Git/GitHub

Job description

Banner Quality Management Inc. seeks an AI Software Developer/Engineer to design, build, deploy, and operate GenAI-enabled data platform capabilities for SMA use cases. The role focuses on AWS-centric data lake architecture, end-to-end data pipelines, and secure APIs for AI workflows.

You will work within a skilled team to implement secure data access, governance, and grounded, source-cited AI outputs, aligning with federal guidelines and enterprise security. Cleveland-based, full-time position.