AI Data Engineer

SAP Taulia

1d•Remote

About The Position

AI is only as smart as the data it consumes. We are seeking an AI Data Engineer to ensure our agent ecosystem is powered by high-quality, structured, and retrieval-ready data. You will serve as the primary bridge between our AI Center of Excellence and existing data teams, coordinating data readiness and architecting the custom integrations or interfaces needed to expose business data to AI tools. By building and managing reusable data pipelines and retrieval architectures, you ensure our AI agents can access the right information securely and performantly, working in lockstep with the AI Solutions Architect to bring high-value agents to life.

Requirements

AI & Search Ecosystem Experience: Demonstrated experience integrating data with Enterprise Search engines and AI agents, or RAG-based systems. You understand what makes data "searchable" for an AI.
LLM & Agent Familiarity: Practical experience preparing data specifically for consumption by Large Language Models and agentic orchestration tools. You know how to structure data to minimize hallucinations.
Data Engineering Experience: 5+ years in data engineering, ETL development, or database management.
Integration Expertise: Strong experience building custom API connectors and data ingestion scripts.
Unstructured Data Expertise: Experience working with unstructured data (text, documents) and NLP concepts.
SQL & Scripting: Strong proficiency in SQL and Python.
Meticulous attention to detail—you care deeply about data cleanliness.
Understanding of enterprise knowledge management challenges.
Ability to audit data sources and identify gaps.
Strong communication skills to work with business owners on data access and cleanup.

Responsibilities

Building and maintaining the custom connectors (APIs, ETL pipelines) required to extract data from core business systems for use in AI tools.
Working with system owners to unlock "siloed" data that is currently inaccessible to our AI ecosystem.
Designing and maintaining the data pipelines that feed our AI knowledge base.
Optimizing "Retrieval-Augmented Generation" (RAG) performance by improving how documents are chunked, tagged, and indexed to reduce hallucinations.
Ensuring data freshness so agents never act on obsolete information.
Creating and maintaining the "AI Data Library" - a comprehensive technical map of where our enterprise data lives, its schema, and its owner.
Working with business teams to identify "Dark Data" (valuable data trapped in PDFs or desktops) and bringing it into the AI ecosystem.
Implementing automated checks to monitor data quality and completeness.
Ensuring sensitive data (PII) is properly flagged and excluded from general AI access where appropriate.