Key skills
PythonSQLAIMLGenerative AIOpenAIRAGETLELTData EngineeringAirflowApache AirflowAWSAzureBedrockGitVersion ControlCI/CDChange Management
About this role
rockITdata is a unique SDVOSB services company that partners with leading commercial healthcare/life sciences organizations on cutting edge innovations. They are seeking an Automation Engineer to design and develop automated metadata harvesting pipelines using Python and SQL, integrating AI/ML capabilities for intelligent metadata extraction.
Responsibilities:
- Design and develop automated metadata harvesting architecture
- Build Python/SQL-based data pipelines for metadata extraction from diverse systems
- Integrate AI tools for intelligent metadata classification and tagging
- Implement Human-in-the-Loop (HITL) validation workflows for AI-assisted harvesting
- Deploy harvesting automation across enterprise systems for scalable metadata capture
- Develop drift detection and alerting mechanisms for metadata change management
- Create and maintain technical documentation for all automation components
- Support empirical testing in sandbox environments for technology evaluations
- Optimize harvesting processes to achieve efficiency gains
- Coordinate with QA teams on automation quality standards
- Troubleshoot and resolve pipeline issues across production environments
Requirements:
- Bachelor's degree in Computer Science, Software Engineering, Data Engineering, or related field
- Minimum 5 years of experience in Python development and SQL
- Experience with AI/ML integration or automation frameworks
- Proficiency with data pipeline tools (Apache Airflow, Prefect, or similar)
- Experience with cloud platforms (AWS, Azure) and their AI/ML services
- Strong understanding of ETL/ELT processes and data integration patterns
- Experience with version control (Git) and CI/CD practices
- Ability to obtain Public Trust clearance
- Experience with Amazon Bedrock, Azure OpenAI, or similar generative AI services
- Knowledge of RAG (Retrieval-Augmented Generation) architecture patterns
- Experience with DoD or federal government IT systems
- Familiarity with FedRAMP-compliant cloud environments (GCC-High)
- Experience with SharePoint APIs and Microsoft Graph
- Knowledge of metadata standards and data catalog integrations