Join our team as a Sr Lead Architect, a Grade 7A position, responsible for spearheading the design and implementation of our enterprise Data & Insights platform on Microsoft Azure. This role requires extensive experience in cloud data architecture, comprehensive data models, and proficiency in data lake/lakehouse environments. You will leverage your expertise in vector-store based RAG systems, GenAI, Agentic AI, and governance with Microsoft Purview.

We are seeking candidates with strong practical skills in Python, LangChain, LangGraph, and Azure data services, coupled with a proven track record of end-to-end SDLC execution.

Architect and design robust Azure-based data lake/lakehouse platforms, including domain data models and efficient ingestion-to-consumption pipelines. Develop conceptual, logical, and physical cloud data models that adhere to enterprise standards.

Architect advanced RAG pipelines, encompassing embeddings, chunking, vector stores, hybrid retrieval, reranking, and evaluation methodologies. Construct Agentic AI workflows utilizing LangChain and LangGraph, focusing on tool orchestration, memory management, and safety layers.

Implement comprehensive data governance strategies with Microsoft Purview for cataloging, lineage tracking, PII classification, and policy enforcement. Ensure platform security through Entra ID, private endpoints, VNETs, Key Vault, and encryption controls.

Lead solution architecture reviews, drive performance tuning, optimize costs, and engineer non-functional requirements. Oversee CI/CD processes with Azure DevOps, Infrastructure as Code using Terraform/Bicep, and implement observability through Azure Monitor and App Insights.

Mentor engineering teams, establish best practices, define architectural patterns, and foster the development of reusable components.

A Bachelor’s or Master’s degree in Engineering, Computer Science, or a related field is required. Possess 12–14 years of overall professional experience, with a minimum of 5+ years dedicated to cloud data architecture.

Demonstrate a strong history of successfully delivering Azure-based data platforms and production-grade GenAI/RAG systems. Proficiency in Python, PySpark, and SQL is essential, alongside hands-on experience with Azure data services like ADLS Gen2, Synapse, Databricks, and ADF.

Expertise in GenAI and Agentic AI, including RAG architecture, vector stores (e.g., Azure Cognitive Search, Pinecone), embeddings, and reranking techniques, is mandatory. Familiarity with frameworks such as LangChain and LangGraph is crucial.

In-depth knowledge of data modeling, including conceptual, logical, and physical models, along with Delta/Parquet patterns and lakehouse principles, is expected. Experience with Microsoft Purview for data governance is also a requirement.