Senior GenAI Data Engineer — Lakehouse Architect (Azure)

Riccione Resources; Dallas (OR); Hybrid; USD 110,000 - 193,000; Full time

Job summary

Riccione Resources in Dallas, TX seeks a Senior Data & GenAI Engineer to architect a new data platform from scratch, setting the patterns, frameworks and architecture that will power AI features across the product.

You’ll build greenfield pipelines with Azure Databricks, implement Medallion Architecture (Bronze-Silver-Gold) on Delta Lake, develop ML-ready datasets and RESTful APIs for GenAI microservices, and collaborate to translate insights into business impact.

Qualifications

• 5 years of hands-on data engineering experience building pipelines from scratch.
• End-to-end Lakehouse architecture design (Bronze/Silver/Gold) using PySpark, Delta Lake, and Azure.
• Experience ETL/ELT with Azure Data Factory and Databricks.
• Experience prepping data for LLM apps, RAG pipelines, vector search, or embeddings.
• Advanced SQL and modular Python development.
• Experience designing RESTful APIs to connect outputs with external services.

Responsibilities

• Build data pipelines from the ground up for a Gen AI data and ML platform.
• Set up greenfield pipelines with Azure Databricks for structured and unstructured data.
• Implement Medallion Architecture using Bronze/Silver/Gold with Delta Lake.
• Develop RESTful APIs for Gen AI microservices and downstream apps.
• Write complex SQL queries and PySpark jobs; optimize partitioning and configs.
• Create ML-ready datasets and a Feature Store.
• Engineer robust ETL/ELT and automated workflows.
• Collaborate to ensure ML solutions deliver business impact.
• Create dashboards and models to turn ML insights into action.

Skills

Data engineering

Azure Databricks

PySpark

Delta Lake

Azure Data Factory

RESTful APIs

SQL

Python

ML pipelines

RAG pipelines

Tools

TensorFlow

Pinecone

Qdrant

ChromaDB

Azure AI Search

Job description

Riccione Resources in Dallas, TX seeks a Senior Data & GenAI Engineer to architect a new data platform from scratch, setting the patterns, frameworks and architecture that will power AI features across the product.

You’ll build greenfield pipelines with Azure Databricks, implement Medallion Architecture (Bronze-Silver-Gold) on Delta Lake, develop ML-ready datasets and RESTful APIs for GenAI microservices, and collaborate to translate insights into business impact.