AI & Data Validation Engineer: Ground Truth & QA

RADcube; Indianapolis (IN); On-site; USD 90,000 - 125,000; Full time

Job summary

RADcube is seeking a Validation Engineer, AI & Data in Indianapolis to ensure the accuracy and reliability of AI-generated responses against approved business requirements and ground truth answers. You will design testing strategies for the Domain Context Model, repository, and ontology mappings, and build automated evaluation tests.

The role focuses on evaluating AI outputs with and without domain context, validating numeric answers, and documenting validation outcomes.

Qualifications

• Bachelor's degree in CS or related field required.
• Experience with data validation and ETL processes.
• Strong SQL and Python programming skills.

Responsibilities

• Design and implement validation strategies for the Domain Context Model and Data Repositories.
• Create ground truth Q&A sets with defined tolerances and clear results.
• Develop automated evaluation tests for AI responses using the Context Injection toolkit.
• Assess AI outputs with and without domain context to measure baseline accuracy and improvements.
• Validate numeric results, SQL queries, business logic and narratives.
• Identify failures such as hallucinations, stale data, and incorrect joins or schemas.
• Develop repeatable evaluation scripts, scoring rubrics, and dashboards for reporting.
• Verify data completeness and access controls across context updates.
• Document test evidence, defects, and remediation results.
• Support release readiness and demonstrations with reusable evaluation frameworks.

Skills

Data quality engineering

SQL

Python

Automated testing

PyTest

ETL

Data validation

AI/LLM evaluation

Ground truth testing

Regression testing

Test automation

Education

Bachelor's degree in Computer Science or related field

Job description

RADcube is seeking a Validation Engineer, AI & Data in Indianapolis to ensure the accuracy and reliability of AI-generated responses against approved business requirements and ground truth answers. You will design testing strategies for the Domain Context Model, repository, and ontology mappings, and build automated evaluation tests.

The role focuses on evaluating AI outputs with and without domain context, validating numeric answers, and documenting validation outcomes.