Data Engineering Consultant: NLP, Lakehouse & Data Quality

Dell Technologies Inc.; Austin (TX); On-site; USD 188,000 - 243,000; Full time

Job summary

Dell Technologies is seeking a data engineering professional to help design design standards and assurance processes for software and data products. You will collaborate with business leaders and internal customers to define requirements and create meaningful insights from unstructured content.

The role emphasizes model-based extraction, entity resolution at scale, and maintaining provenance along the data journey, with a focus on lakehouse architectures and efficient data orchestration.

Qualifications

• Strong experience with NLP/LLM-based extraction and document understanding.
• Proficient PySpark and lakehouse/medallion data architectures in production.
• Expertise in entity resolution and record linkage at scale.
• Familiar with data provenance and cross-system lineage.

Responsibilities

• Take landed data through the medallion stages (Bronze-Silver-Gold) with traceable lineage.
• Own entity resolution to produce a canonical identity.
• Build model-based extraction lanes to pull structure from unstructured content across different content types.
• Tag provenance and trust tier on every record and quarantine what fails the gate.
• Keep high-volume data in the lakehouse and the served layer lean and fast.

Skills

NLP/LLM extraction

PySpark

Lakehouse

Entity resolution

Airflow

Provenance mindset

Job description

Dell Technologies is seeking a data engineering professional to help design design standards and assurance processes for software and data products. You will collaborate with business leaders and internal customers to define requirements and create meaningful insights from unstructured content.

The role emphasizes model-based extraction, entity resolution at scale, and maintaining provenance along the data journey, with a focus on lakehouse architectures and efficient data orchestration.