Responsibilities

- 7 to 10 years of experience in data engineering and minimum of 3+ years of experience working in Databricks
- 4+ years Working in leveraging Pyspark for building reusable Data ingestion and Data quality frameworks
- Lakehouse & Data Engineering: Design scalable batch and real-time ETL pipelines using PySpark, Structured Streaming, and Delta Lake built on a Medallion Architecture (Bronze, Silver, Gold).
- ABAC and RBAC Security
- Experience in setting up ABAC and RBAC security for Agentic AI Journey use cases
- Agentic AI & Orchestration: Build autonomous, multi-agent workflows and reasoning loops using MCP Protocol and Serverless compute.
- RAG & Vector Integration: Develop end-to-end Retrieval-Augmented Generation (RAG)



pipelines and integrate vector databases for semantic retrieval.
- Governance & Operations: Manage data lineage, access controls, and security using Unity Catalog alongside CI/CD workflows and LLM evaluation frameworks

Key Skills

- Databricks
- PySpark
- Structured Streaming
- Delta Lake
- Medallion Architecture
- ABAC
- RBAC
- Agentic AI
- MCP Protocol

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 Amaze - Cloud Data Architect (Navi Mumbai)
🏢 Hexaware Technologies
📍 Navi Mumbai