AI Data Engineer: RAG & Vector Pipeline Expert

Machine Learning Technologies, LLC; Scottsdale (AZ); On-site; USD 110,000 - 170,000; Full time

Job summary

Machine Learning Technologies, LLC in Scottsdale, AZ seeks an experienced AI Data Engineer to design and maintain scalable data pipelines and infrastructure for AI/ML, RAG, and LLM applications. Strong SQL, Python/Scala, and cloud data platforms with handling of structured and unstructured data are essential.

The role emphasizes building embedding pipelines, vector databases, data quality, governance, lineage, and access controls while supporting ML model training, inference, and MLOps workflows

Qualifications

• Proficiency in SQL and Python/Scala for data pipelines (structured and unstructured data).
• Experience with Apache Airflow and dbt for orchestrating data workflows.
• Experience with RAG, vector databases, embeddings and vector search.
• Handling structured and unstructured data such as PDFs, documents and transcripts.
• Knowledge of ML lifecycle, MLOps and LLMOps workflows.

Responsibilities

• Design and develop data ingestion, transformation, and processing pipelines.
• Build embedding pipelines and integrate vector databases.
• Develop data pipelines supporting RAG, chunking, and vector search.
• Process structured and unstructured data (PDFs, documents, logs, transcripts).
• Implement data quality, governance, lineage, and access controls.
• Support ML model training, inference, MLOps, and LLMOps workflows.
• Optimize data pipelines for performance, scalability, and cost.

Skills

SQL

Python/Scala

Airflow/dbt

RAG/Vector DBs

Unstructured data processing

ML lifecycle

Job description

Machine Learning Technologies, LLC in Scottsdale, AZ seeks an experienced AI Data Engineer to design and maintain scalable data pipelines and infrastructure for AI/ML, RAG, and LLM applications. Strong SQL, Python/Scala, and cloud data platforms with handling of structured and unstructured data are essential.

The role emphasizes building embedding pipelines, vector databases, data quality, governance, lineage, and access controls while supporting ML model training, inference, and MLOps workflows