Data Engineer: NLP, Lakehouse & Provenance

Dell Inc.; Round Rock (TX); Hybrid; USD 188,000 - 243,000; Full time

Job summary

Dell Technologies seeks an experienced data engineer to define design standards and assurance processes for software, data and analytics initiatives. You will translate business goals into data architectures, build model-based extraction lanes for unstructured content, and ensure provenance and traceability across the data lifecycle.

The role emphasizes lakehouse/medallion data pipelines, NLP/LLM-driven extraction, and scalable entity resolution to deliver accurate business insights in a

Qualifications

• Experience with unstructured data using NLP/LLM-based extraction and embeddings.
• Proficient PySpark and lakehouse/medallion architectures in production.
• Experience with entity resolution and record linkage at scale.
• Familiar with data provenance and data lineage.

Responsibilities

• Take landed data through the medallion (Bronze → Silver → Gold) with traceable lineage.
• Own entity resolution to produce a canonical identity.
• Build model-based extraction lanes (NLP/LLM) to pull structure from unstructured content.
• Tag provenance and trust tier on records and quarantine failed data with reasons.
• Keep high-volume data lean in the lakehouse and served layer.

Skills

NLP

LLM-based extraction

Document understanding

Embeddings

PySpark

Lakehouse

Entity resolution

Airflow

Provenance

Job description

Dell Technologies seeks an experienced data engineer to define design standards and assurance processes for software, data and analytics initiatives. You will translate business goals into data architectures, build model-based extraction lanes for unstructured content, and ensure provenance and traceability across the data lifecycle.

The role emphasizes lakehouse/medallion data pipelines, NLP/LLM-driven extraction, and scalable entity resolution to deliver accurate business insights in a