AI Data Architect

BraunAbility•Winamac, IN

About The Position

Essential Functions: Data Pipelining & Infrastructure Build, optimize, and maintain the data pipelines that feed BAA's AI solutions, connecting both structured and unstructured data from enterprise data lakes (Snowflake), ERP systems (Epicor), CRM (Salesforce), and document repositories (SharePoint). Automate the ingestion and structuring of unstructured data (PDFs, manuals, contracts, emails) to enable highly accurate Retrieval-Augmented Generation (RAG) architectures. Map complex enterprise data schemas to identify the exact tables, fields, and payloads required to support the cognitive architecture designed by the AI Studio Lead. Build and maintain development and testing environments that allow the Studio to experiment rapidly without risking production systems. Security, Governance & Compliance Design and implement strict Role-Based Access Control (RBAC) and enterprise security protocols within the AI environment — ensuring AI agents only query data explicitly authorized for the specific end-user. Prevent data leakage across departments by structurally constraining what each AI model can access at the pipeline level, not just the application level. Serve as the formal infrastructure checkpoint before cognitive architecture development begins — confirming pipeline stability, RBAC compliance, and data integrity prior to any build phase commencing. Monitor data flows for system drift, broken APIs, or context collapse, ensuring AI outputs remain accurate and safe for both office and factory floor operations. Establish and maintain Service Level Agreements (SLAs) for pipeline uptime — detecting and communicating failures before end-users are impacted. Platform Integration & IT Liaison Develop secure API integrations between enterprise AI platforms and BAA's existing technology stack. Serve as the primary technical liaison to BAA IT and Global Data Architecture, ensuring infrastructure provisioning, database access, and cloud networking meet enterprise standards. Advocate for the AI Studio's technical needs within the broader IT governance ecosystem. Implement automated alerting systems for data pipeline failures.

Requirements

Deep technical expertise working with SQL, enterprise data lakes, and ETL/ELT pipeline construction.
Strong proficiency in building and securing API integrations between disparate cloud and on-premises systems.
Experience implementing strict security frameworks and Role-Based Access Controls (RBAC) at the database and application layer.
Exceptional troubleshooting and debugging skills.
Comfort operating in a small, fast-moving team where you own entire workstreams end-to-end.
Bachelor’s degree and minimum of 6 years of related work experience required. An equivalent combination of education and/or related work experience equal to 10 years will also be considered.
3+ years of experience in data engineering, data architecture, or database administration within an enterprise environment.

Responsibilities

Build, optimize, and maintain data pipelines for AI solutions, connecting structured and unstructured data from various enterprise systems.
Automate ingestion and structuring of unstructured data for RAG architectures.
Map enterprise data schemas to identify required data for AI cognitive architecture.
Build and maintain development and testing environments for AI experimentation.
Design and implement Role-Based Access Control (RBAC) and enterprise security protocols within the AI environment.
Prevent data leakage across departments by constraining AI model data access.
Serve as an infrastructure checkpoint before cognitive architecture development.
Monitor data flows for system drift, broken APIs, or context collapse.
Establish and maintain Service Level Agreements (SLAs) for pipeline uptime.
Develop secure API integrations between enterprise AI platforms and existing technology stack.
Serve as the primary technical liaison to BAA IT and Global Data Architecture.
Advocate for AI Studio's technical needs within IT governance.
Implement automated alerting systems for data pipeline failures.