Senior Data & AI Engineer

Senior Data & AI
Engineer

Location: Carmel, Indiana
Experience: 6–10 years
Employment Type: Full-time

About the Role

RADcube is hiring a hands-on
Senior Engineer who knows data, AI, and the business. You will dig into complex
enterprise schemas, work out what the data means to the business, and build the
models, semantic layers, and metadata that let AI systems answer questions
accurately. You will contribute directly to our RADLabs accelerators, including
generative BI and agentic platforms, and to client work in pharma, life
sciences, and healthcare.

What You'll Do

Schema & Data Modeling

• Build and maintain data models
  (dimensional, relational, lakehouse) that follow team standards.
  
• Explore and document unfamiliar or
  legacy schemas, producing ER diagrams, data dictionaries, join paths, and
  lineage.
  
• Develop and optimize SQL,
  transformations, and pipelines on cloud data platforms.
  

Semantic Layer & AI
Enablement

• Translate raw tables into business-friendly
  semantic models: metrics, dimensions, hierarchies, and relationships.
  
• Write and enrich schema metadata and
  descriptions to improve LLM text-to-SQL and generative BI accuracy.
  
• Work with AI engineers on RAG pipelines,
  agent tools, and prompt design where structured data is involved.
  
• Test and evaluate AI-generated queries
  for correctness, and help build test sets and guardrails.
  

Business Understanding

• Take part in client discovery sessions
  to understand processes, KPIs, and reporting needs.
  
• Turn business questions into data
  requirements and validate metric definitions with stakeholders.
  
• Explain data findings clearly to both
  technical and non-technical audiences.
  

Quality & Collaboration

• Apply data quality checks, naming
  standards, and documentation practices.
  
• Follow governance and compliance
  requirements (GxP, HIPAA) where relevant.
  
• Review peers' work and support junior
  engineers when needed.
  

Requirements

What You Bring

Must-Have

• 6+ years in data engineering, analytics
  engineering, or BI development.
  
• Strong SQL and solid understanding of
  relational and dimensional modeling.
  
• Demonstrated ability to learn and
  navigate large enterprise schemas (SAP, Salesforce, MES, or similar).
  
• Hands-on experience with AWS (Redshift,
  Glue, Athena, S3) and/or Azure (Synapse, Fabric, Data Factory), plus
  Databricks or Snowflake.
  
• Proficiency in Python for data work.
  
• Practical exposure to LLMs on structured
  data, such as text-to-SQL, semantic layers, or AI-assisted analytics.
  
• Good business sense and comfort talking with
  stakeholders about KPIs and processes.
  

Nice-to-Have

• Experience in pharma, life sciences,
  manufacturing and quality, or healthcare data.
  
• dbt, or semantic layer tools such as
  Cube, dbt Semantic Layer, or LookML.
  
• Familiarity with vector databases,
  knowledge graphs, or agentic frameworks (LangChain/LangGraph, Bedrock
  Agents, MCP).
  
• Data catalog tools such as Unity
  Catalog, Collibra, or AWS DataZone.
  
• AWS, Azure, or Databricks
  certifications.
  

What Success Looks Like (First 6 Months)

• Semantic models and metadata are
  delivered for at least one accelerator or client use case.
  
• AI-generated query accuracy measurably
  improves on the datasets you own.
  
• Schema documentation is good enough that
  others on the team can pick it up and run with it.
  
• Stakeholders trust you to understand
  both their data and their business.