Back to SearchSenior AI Solution Engineer with MS Foundry, MCP
Remote in Armenia, & 4 others
AI Solution Engineering& 29 others
Looking for something else?
Find a vacancy that works for you. Send us your CV to receive a personalized offer.
Find me a job
Choose an option
We are seeking a Senior AI Solution Engineer with expertise in MS Foundry and MCP to build automated data ingestion pipelines and data scraping mechanisms on Azure Databricks that fuel the enterprise AI platform and semantic layer. This role focuses on gathering structured and unstructured data, automating workflows via Azure DevOps CI/CD pipelines, and exposing clean data models formatted via Open Knowledge Format directly to Databricks semantic layers, AI Search, and AI agent runtimes.
Responsibilities
- Build high-throughput data ingestion pipelines and data scraping engines using Python, PySpark, and Databricks Auto Loader to collect unstructured document content, external registry feeds, and enterprise data
- Structure and expose ingested data within the Databricks semantic layer, organize datasets using Open Knowledge Format standards for seamless consumption by AI Search, Databricks Genie Spaces, and LLM reasoning engines
- Automate ingestion pipeline deployments, scraping job schedules, and code releases using Azure DevOps and Databricks Asset Bundles (DABs)
- Scrape and ingest healthcare and insurance data sources, including regulatory databases, public registries, and unstructured medical/claims files, to support AI agent workflows
- Implement schema enforcement, automated ingestion failure alerts, and job telemetry within Databricks Workflows and Azure DevOps
Requirements
- Extensive experience (5+ years) building high-volume data ingestion pipelines using Azure Databricks, PySpark, and Auto Loader
- Hands-on experience developing data scraping routines and extraction engines for complex, unstructured data sources
- Proven ability to structure ingested datasets using the Open Knowledge Format within Databricks semantic layers and AI Search for downstream GenAI consumption
- Track record of managing Databricks ingestion workflows and deployment pipelines using Azure DevOps and Databricks Asset Bundles (DABs)
- English proficiency at B2 level or higher