AI Data Engineer

Cinteot Inc. is a small IT services company that specializes in cybersecurity, Big Data/databases, software development, systems testing, STIG Compliance training, closed-circuit television/security cameras and access controls, and construction/facilities.

We are a Woman-owned, SBA Certified 8(a), and HUBZone company.

Job Overview

The AI Data Engineer is responsible for building and operating high‑quality, governed, and AI‑ready data pipelines that power enterprise GenAI and agent‑based use cases. This role focuses on preparing data for retrieval‑augmented generation (RAG), managing embeddings and vector indexes, and ensuring data quality, lineage, and compliance across the AI platform. As part of the AI CoE Technology pod, the AI Data Engineer enables rapid, responsible AI development by delivering reusable, scalable data foundations. This is a hands‑on individual contributor role within the AI CoE – Technology pod, working closely with AI Platform Engineers and AI Engineers to support both shared platform capabilities and priority AI use cases. The role is intentionally centralized to avoid fragmented data pipelines and to ensure consistent governance, quality, and reuse across the enterprise.

Major Responsibilities

• Design, build, and maintain data pipelines that ingest, transform, and curate structured and unstructured data for AI use cases.
• Prepare RAG‑ready datasets by applying metadata enrichment, chunking, normalization, and document parsing patterns aligned to platform standards.
• Partner with source system teams and domain SMEs to understand data semantics and ensure accurate representation for AI consumption.

• Create and maintain embedding pipelines, including generation, refresh, and lifecycle management.
• Own vector index maintenance, including re‑indexing strategies, performance tuning, and cleanup of stale or unused embeddings.
• Support knowledge grounding for AI agents by ensuring source attribution, consisten