Senior Data & AI Engineer

RADcube is looking for a Senior Data & AI Engineer to help build the data foundation that makes AI-driven answers reliable. In this onsite role in Carmel, Indiana, you will design semantic models, create high-quality metadata, and connect structured data with AI capabilities like text-to-SQL and RAG.

You’ll work across cloud data platforms, collaborate with AI engineers on structured-data use cases, and partner with clients to translate business questions into well-defined data requirements. The focus is on accuracy, clarity, and governance, including environments where GxP and HIPAA may apply.

What you’ll do

• Build and maintain data models (dimensional, relational, and lakehouse) aligned with team standards.
• Investigate and document unfamiliar or legacy schemas, including ER diagrams, data dictionaries, join paths, and lineage.
• Develop and optimize SQL, transformations, and pipelines on cloud data platforms.
• Create business-friendly semantic models by translating raw tables into metrics, dimensions, hierarchies, and relationships.
• Write and enrich schema metadata and descriptions to support LLM text-to-SQL and generative BI accuracy.
• Collaborate with AI engineers on RAG pipelines, agent tools, and prompt design when structured data is involved.
• Test and evaluate AI-generated queries for correctness, including help building test sets and guardrails.
• Participate in client discovery sessions to understand processes, KPIs, and reporting needs.
• Convert business questions into data requirements, validating metric definitions with stakeholders.
• Communicate data findings clearly to technical and non-technical audiences.
• Apply data quality checks, naming standards, and documentation practices.
• Follow governance and compliance requirements where relevant (GxP, HIPAA).
• Review peers’ work and support junior engineers as needed.

Skills and experience

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

Technologies you may work with

• SQL, Python
• AWS: Redshift, Glue, Athena, S3, AWS DataZone
• Azure: Synapse, Fabric, Data Factory
• Databricks, Snowflake
• SAP, Salesforce, MES
• LLMs, text-to-SQL, RAG
• LangChain, LangGraph, Bedrock Agents, MCP
• Unity Catalog, Collibra
• dbt, Cube, dbt Semantic Layer, LookML
• Vector databases, knowledge graphs, agentic frameworks

Nice-to-have

• Experience with pharma, life sciences, manufacturing and quality, or healthcare data.
• Experience with dbt and/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).
• Experience with data catalog tools such as Unity Catalog, Collibra, or AWS DataZone.
• AWS, Azure, or Databricks certifications.

What success looks like in the first 6 months

• Deliver semantic models and metadata for at least one accelerator or client use case.
• Achieve measurable improvements in AI-generated query accuracy on datasets you own.
• Produce documentation that enables others on the team to pick up and extend the work.
• Earning stakeholder trust by demonstrating strength in both their data and their business context.