NLP-Driven Data Engineering Architect

Dell; Town of Texas (WI); On-site; USD 188,000 - 243,000; Full time

Benefits offered by this job

Benefits program

Job summary

Dell Technologies seeks a data analytics engineer to design standards and assurance processes for software development, focusing on unstructured data, data lakes, and model-driven insights. You will define requirements, build extraction lanes with NLP/LLM, ensure provenance, and maintain fast, auditable data products across the medallion to gold pipeline.

Experience with PySpark, Airflow, and lakehouse architectures is essential to keep data flowing and trusted for business insights.

Qualifications

• Strong model expertise for unstructured data - NLP and LLM-based extraction, document understanding, embeddings.
• Strong PySpark and lakehouse / medallion experience in production.
• Entity resolution / record linkage at scale.
• Airflow or comparable orchestration.
• A provenance mindset - "where did this come from" is a first-class column to you.

Responsibilities

• Take landed data through the medallion (Bronze to Gold) - conform structured sources and extracted content to Gold within its freshness SLA, with traceable lineage.
• Own entity resolution - the resolve gate that turns multiple sources into one canonical identity.
• Build the model-based extraction lanes - NLP and LLM-assisted - that pull structure out of unstructured content across different content types, tagged as evidence, not fact.
• Tag provenance and trust tier on every record; quarantine what fails the gate with its reason, rather than dropping it.
• Keep high-volume data in the lakehouse and the served layer lean and fast.

Skills

NLP & LLM extraction

Embeddings

Document understanding

Entity resolution

Data lakehouse

Model development

Tools

PySpark

Airflow

Lakehouse/Medallion

Data lineage tools

Job description

Dell Technologies seeks a data analytics engineer to design standards and assurance processes for software development, focusing on unstructured data, data lakes, and model-driven insights. You will define requirements, build extraction lanes with NLP/LLM, ensure provenance, and maintain fast, auditable data products across the medallion to gold pipeline.

Experience with PySpark, Airflow, and lakehouse architectures is essential to keep data flowing and trusted for business insights.