Data Engineering Consultant — NLP, Lakehouse & Scale

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

Benefits offered by this job

Dell Benefits Program

Job summary

Dell Inc. is seeking a data-focused professional to establish design standards and assurance processes for software and data systems.

You will define requirements, generate business insights, and develop new approaches to derive meaning from data, covering data analysis, architecture, and consulting across teams. You will work with model-based extraction, lineage, and data governance to ensure accuracy and operability, while enabling scalable analytics across platforms.

Qualifications

• Strong experience with unstructured data, NLP, and LLM-based extraction for document understanding.
• Hands-on PySpark experience in production data lakes/medallion architectures.
• Expertise in linking and resolving entities at scale with lineage and provenance awareness.

Responsibilities

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

Skills

NLP/LLM extraction

PySpark

Document understanding

Embeddings

Entity resolution

Data governance

Tools

Airflow

Lakehouse

Job description

Dell Inc. is seeking a data-focused professional to establish design standards and assurance processes for software and data systems.

You will define requirements, generate business insights, and develop new approaches to derive meaning from data, covering data analysis, architecture, and consulting across teams. You will work with model-based extraction, lineage, and data governance to ensure accuracy and operability, while enabling scalable analytics across platforms.