Data Engineer/Architect
Artificial Intelligence
Azure
Big Data
Cloud
Cloud Data Engineering
Cloud Data Platform
Cloud Engineer
Cloud Operations
Cloud Platform
Cloud Platforms
Cloud Platforms Cloud Platforms
Data
Data Analysis
Data Analytics
Data Architecture
Data Engineer
Data Engineering
Data Integration
Data Integration Tools
Data Pipeline
Data Platform
Data Processing
Data Warehouse
Database
Databases
Engineer
ETL
Informatica
Information Technology (IT)
Programming Languages
Rag Systems
Reporting and Analytics
Software Development
SQL
Vector Databases
Job Description
Kavant Solutions is seeking a Data Engineer/Architect to help build the data foundations that AI use cases depend on in a federal and regulated context. This role focuses on data readiness, governed access, secure pipelines, and data quality capabilities, along with preparing unstructured content for RAG.
This position is remote within the United States and supports AI engineering through reliable data architectures and well-documented interfaces.
Role Focus
- Evaluate data availability, quality, and readiness during discovery for prioritized candidate AI use cases, and flag risks that could impact feasibility.
- Design data architectures for source-to-target data flows, including storage patterns and data models aligned to analytics and AI workloads.
- Build and maintain data pipelines to ingest, cleanse, transform, and deliver data from enterprise systems and authoritative sources.
- Prepare and structure unstructured content (documents, policies, knowledge articles) for retrieval-augmented generation (RAG), including chunking, metadata, embeddings, and vector index design.
- Define access, privacy, and handling controls for sensitive data, including PII and PHI, aligned with federal and client requirements.
- Implement data quality checks, lineage, and monitoring to ensure pilots produce trustworthy, measurable outcomes.
- Work with the AI Solutions Architect and AI product engineers to hand off documented data interfaces and contribute reusable data patterns to the program’s workflow library.
What You Bring
- 5+ years of relevant professional experience, including designing and building production data pipelines and data platforms for analytics, machine learning, or AI solutions.
- Strong proficiency in SQL and Python, including data modeling for relational, dimensional, and lakehouse environments.
- Working knowledge of Microsoft Azure or AWS data services, including options such as Azure Data Factory, Databricks, Microsoft Fabric, Synapse, AWS Glue, or Amazon Redshift.
- Hands-on experience preparing data for large language model applications, including document processing, embeddings, and vector stores such as Azure AI Search or Amazon OpenSearch.
- Experience implementing data governance, security, and access controls for sensitive data in federal or regulated environments.
- Strong written and verbal communication with both technical and non-technical audiences.
- A Bachelor’s degree in a related field.
Technologies
- SQL, Python
- Azure Data Factory, Databricks, Microsoft Fabric, Synapse
- AWS Glue, Amazon Redshift
- Azure AI Search, Amazon OpenSearch
- RAG, lakehouse
Clearance
- Must be able to obtain and maintain a federal Public Trust background investigation and an agency-issued PIV credential.
Compensation and Schedule
- Salary: USD 125,000 to 175,000 per year
- Work arrangement: Remote (must reside in the United States)
- Schedule: Flexible schedule
Benefits
- 401(k)
- 401(k) matching
- Paid time off
- Retirement plan
Additional Plus Factors
- A master’s degree is preferred.
- Experience with VA or other federal health data systems and data sharing agreements.
- Microsoft Certified Azure Data Engineer Associate, Databricks Certified Data Engineer Professional, AWS Certified Data Engineer Associate, or similar.
Sponsorship question: Will you now, or in the future, require sponsorship from an employer?