Domain: Production GenAI / RAG / Agentic Systems Data Architecture
Неизвестный работодатель · На сервисе с: 02.10.26 18:14
id 7114
Enterprise Azure Data Architect (GenAI & RAG Data Layer)
📍 Format: Belarus
Domain: Production GenAI / RAG / Agentic Systems Data Architecture
We are looking for an experienced Enterprise Azure Data Architect with deep expertise in building robust data platforms and the Data Layer supporting production-grade GenAI, RAG, and Agentic AI applications.
❌ Who this role is NOT for:
NOT an AI/LLM Developer: We are not looking for someone writing agent code, doing prompt engineering, or coding with LangChain/LlamaIndex.
NOT a pure DevOps / Infra Engineer: We are not looking for a Kubernetes (AKS), Terraform, or CI/CD pipeline specialist.
✅ Who we ARE looking for:
An Enterprise Data Architect who designs the critical "underwater part of the iceberg" — the end-to-end Data & Knowledge Layer powering AI systems:
Ingestion & Preparation: How enterprise data (documents, unstructured text, databases) is ingested, cleaned, chunked, and formatted for AI consumption using Azure Synapse, Databricks, and ADF.
Storage & Retrieval: Designing vector search and hybrid retrieval systems (Azure Cosmos DB, Azure SQL, Lakehouse) to support real-time RAG and AI Agents.
Architecture & Governance: Data modeling, metadata-driven ingestion, RBAC, security, and scalability in high-load production environments.
🛠 MUST-HAVE Requirements:
Real Production RAG / Agentic Data Layer Experience: Proven track record of designing data platforms for live GenAI/RAG/Agentic applications (not just POCs or pilot projects).
Azure Cosmos DB: Deep hands-on design experience (fundamental requirement, including NoSQL, partitioning, and Vector Search capabilities).
Azure Synapse Analytics: Strong architecture ownership and deep practical experience with specific Synapse features (SQL pools, pipelines, Spark).
Azure Data Platform Stack: Azure Databricks, Azure Data Lake (ADLS Gen2 / Lakehouse), Azure SQL MI / SQL Server / T-SQL, Azure Functions.
Unstructured & Structured Data: Deep experience handling complex unstructured data alongside enterprise structured data.
Modernization & Metadata-driven Architecture: Proven experience in data platform modernization and metadata-driven ingestion design.
📌 Critical Requirements for Candidates' CVs:
Note from Hiring Managers: Candidates will only be considered if their CV clearly reflects and details the specific project experience matching the requirements above.
❗️❗️❗️Писать ••••••••⚡️⚡️⚡️⚡️ С РЕЗЮМЕ В КОТОРОМ УКАЗАН ВОЗРАСТ И ЛОКАЦИЯ НАХОЖДЕНИЯ. Укажите 🆔 вакансии❗️ Без этой информации отклики не рассматриваются
HireSeeker собирает вакансии со всех площадок и присылает только релевантные. Бесплатно.