Data & AI Engineer
Location: Indianapolis, IN
Summary: Develop and integrate the technical components that capture, store, process, and deliver business context to the client’s existing AI ecosystem.
Responsibilities:
- Develop and maintain the Business Context Repository in a client approved environment, using the architecture and standards established for the project.
- Build data integration pipelines to capture business context from approved sources, including metadata registries, catalogs, workshop outputs, BI reports, and usage information.
- Implement structured storage and retrieval mechanisms for business definitions, ontology relationships, metadata, business rules, and ground truth datasets.
- Integrate the repository with the client’s existing Context Injection component and relevant Graph, semantic, and metadata services.
- Develop Python based automation to extract, transform, validate, and refresh business context.
- Implement LLM assisted and agentic workflows for context drafting, enrichment, review, and maintenance, including human approval controls.
- Build scheduled refresh processes, staleness detection, logging, and monitoring mechanisms.
- Support development of the AI evaluation runner, execute technical integrations, troubleshoot failures, and maintain deployment configurations.
- Deliver reusable source code, configuration, technical documentation, and operational runbooks to the client’s designated repositories.
Requirements
Skills Required
- Strong hands-on data engineering background
- Python, PySpark/Spark, and SQL experience
- Databricks experience, including Delta Lake and Lakehouse
- Strong hands-on experience with AWS data services
- ETL/ELT pipeline development and data modeling experience
- Experience with batch and streaming ingestion, data quality, governance, and CI/CD
- Ability to independently engage stakeholders and translate requirements into solutions
- Excellent communication and stakeholder management skills
- Must be local to Indianapolis, Indiana and able to work onsite
- Experience with Unity Catalog, MLflow, or Medallion Architecture
- Databricks certification
- Azure experience
- NVIDIA ecosystem exposure
- GenAI and machine learning pipeline experience
- Regulated healthcare or pharmaceutical experience
- Experience identifying additional technology or business opportunities
What We Do
RADcube is a technology consulting and software development firm founded in 2015 and headquartered in Carmel, Indiana. It helps organizations turn enterprise ideas into practical innovations through digital transformation, custom software, data analytics, artificial intelligence, cloud computing, cybersecurity, and intelligent automation. The company serves healthcare, finance, government, and manufacturing clients, combining human-centric delivery with responsible, accountable technology solutions designed to produce measurable business outcomes.








