Consultant, Data Engineering

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

SUMMARY

Interacts with business leaders and internal customers to create and establish design standards and assurance processes for software, systems and applications development to ensure compatibility and operability. Analyzes business goals, defines project scope and identifies functional and technical requirements to produce accurate business insights. Develops fundamentally new approaches to generate meaning from data, creating specifications for reports and analysis based on business needs. Job disciplines may include data analysis and science, data architecture and solutions engineering, visual design and analytics enablement and internal consulting.

ACCOUNTABILITIES

• Take landed data through the medallion (Bronze > Silver > Gold) - conform structured sources (e.g. CPQ / PIM) 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 (e.g. HTML), 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.

Essential Requirements:

• Strong model expertise for unstructured data - NLP and LLM-based extraction, document understanding, embeddings. This is a core need for the pod.
• 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.

Compensation

Dell is committed to fair and equitable compensation practices. The salary range for this position is USD $187,850 to USD $243,100

Benefits and Perks of working at Dell Technologies

Your life. Your health. Supported by your benefits. You can explore the overall benefits experience that awaits you as a Dell Technologies team member - right now at MyWellatDell.com