Data Engineer

Responsibilities

• Architect and deploy ingestion pipelines to extract high-volume transactional data from SAP S/4HANA, Ariba, and PLM systems
• Build connectors for external market intelligence feeds to enrich internal procurement data
• Design and implement standardized procurement data models and taxonomies across multiple entities
• Engineer pipelines to process unstructured technical data (PDFs, CAD metadata) into vector-ready formats for RAG applications
• Manage and optimize Vector Databases like Weaviate to ensure high-speed retrieval for AI tools
• Implement defense-grade security protocols, including RBAC, audit logging, and data redaction
• Deploy automated data quality frameworks to validate Bill of Materials (BOM) and cost data accuracy
• Optimize pipelines for on-premise GPU clusters and air-gapped environments

Requirements

• 5+ years of experience in Data Engineering
• 2+ years of experience building ML or Generative AI pipelines in an enterprise setting
• Expert proficiency in Python and SQL
• Hands-on experience with Apache Spark, Kafka, and Airflow
• Deep expertise in SAP S/4HANA and SAP Ariba
• Knowledge of Databricks, Delta Lake, and relational databases like PostgreSQL
• Experience with Vector Databases such as Weaviate or Milvus
• Proficiency with containerization tools including Docker and Kubernetes

Preferred Qualifications

• Experience in the Supply Chain, Manufacturing, or Defense sectors
• Familiarity with SAP BTP
• Experience with data orchestration tools like dbt, Dagster, or Prefect
• Understanding of Model-Based Systems Engineering (MBSE) and the "Digital Thread"

About the Company

AI71 is building the foundational data infrastructure and defense-grade Data Lakehouses required to power AI agents and intelligent supply chain forecasting for EDGE Group’s AI transformation.