Senior Data Engineer — AI Data Platforms & Vector AI

TechDigital Group; Dearborn (MI); On-site; USD 120,000 - 180,000; Full time

Job summary

TechDigital Group in Dearborn, MI seeks a Senior Data Engineer to build AI-ready data platforms, integrate new data sources into VESSEL, enable vectorization, and lay the data foundations for Agentic AI, Retrieval-Augmented Generation (RAG), and intelligent agents.

You will design cloud-native pipelines, vector databases, semantic search, and data services to support AI agents and prompt engineering, while maintaining data quality, governance, and scalable performance.

Qualifications

• 10+ years of experience in Data Engineering.
• Strong expertise in Python, Spark, SQL and data processing frameworks.
• Experience building cloud-native data pipelines.
• Deep understanding of vector databases and embeddings.
• Experience with Retrieval-Augmented Generation (RAG).
• Knowledge of Agentic AI architectures.
• Experience designing metadata-driven data solutions.

Responsibilities

• Integrate structured and unstructured data sources into VESSEL.
• Design and implement data ingestion pipelines.
• Create vectorized data repositories for AI applications.
• Develop semantic search and knowledge retrieval frameworks.
• Build data services supporting AI agents and prompt engineering.
• Design scalable cloud-native data platforms.
• Optimize data quality, governance, and performance.

Skills

Data Engineering

Python

Spark

SQL

Cloud data pipelines

Vector databases

Embeddings

RAG

Agentic AI

Metadata-driven design

Job description

TechDigital Group in Dearborn, MI seeks a Senior Data Engineer to build AI-ready data platforms, integrate new data sources into VESSEL, enable vectorization, and lay the data foundations for Agentic AI, Retrieval-Augmented Generation (RAG), and intelligent agents.

You will design cloud-native pipelines, vector databases, semantic search, and data services to support AI agents and prompt engineering, while maintaining data quality, governance, and scalable performance.