About
We are only considering candidates with strong, hands‑on experience in: Building production‑grade ETL/ELT pipelines using Python and SQL Designing and operating data transformation layers (dbt or equivalent) Production experience with vector databases (PGVector, ChromaDB, Pinecone, Weaviate or similar) Production experience with graph databases (Neo4j or equivalent) Designing data models for complex relational domains Implementing secure data access layers (no direct DB access from downstream systems) Multi‑tenant data isolation and data governance Strong AWS experience (S3, RDS, event‑driven architectures) Highly Desirable
Experience with Model Context Protocol (MCP) or governed AI data interfaces Temporal or long‑running workflow orchestration Commercial Real Estate, finance, or similarly complex structured domains The Role
You will architect and build the agent‑ready data layer, including ETL pipelines, vector and graph stores, and governed APIs that ensure AI agents only access curated, secure, and structured data. You will also help define how enterprise data is transformed into formats suitable for RAG systems and autonomous agent reasoning, while ensuring strict security and isolation standards across tenants. This role requires hands‑on production experience building data platforms at scale. Candidates whose experience is primarily BI/reporting, ad‑hoc analytics, or non‑production pipelines will not be suitable.
#J-18808-Ljbffr
Languages
- English
Notice for Users
This job comes from a TieTalent partner platform. Click "Apply Now" to submit your application directly on their site.