Job Purpose

To design and deliver AI-powered Business Intelligence solutions by integrating Databricks Genie, PowerBI Co-Pilot Semantic Models, and Metric Views on top of a robust end-to-end data engineering stack. The role focuses on enabling self-service analytics using natural language (GenAI), ensuring business-friendly data consumption, and building governed, scalable, and high-performance data ecosystems across batch and real-time pipelines.

Duties and Responsibilities

- Translate business problems into AI-driven BI solutions
- Own end-to-end delivery: ingestion transformation semantic layer AI consumption
- Design scalable data architecture aligned with lakehouse principles
- Ensure data quality, governance, and metric consistency
- Collaborate with business teams to onboard them onto Genie-based analytics
- Optimize performance of queries, pipelines, and AI responses
- Establish best practices for AI in BI (prompting, semantic tuning, governance)
- Drive adoption of self-service BI with minimal dependency on tech teams

Key Decisions / Dimensions

- Define semantic layer design and metric definitions
- Decide GenAI prompting strategies and instruction frameworks
- Prioritize data vs AI optimization trade-offs
- Handle production issues with RCA and long-term fixes
- Drive architectural decisions for lakehouse + AI integration





Major Challenges

- Ensuring accuracy and trust in AI-generated insights
- Driving adoption of GenAI-based BI over traditional dashboards
- Maintaining semantic consistency across multiple tools
- Balancing performance, cost, and scalability
- Managing dependencies across data engineering, AI, and business teams

Required Qualifications and Experience

- Azure Databricks - PySpark, SQL, Delta Lake
- PowerBI - CoPilot, Semantic Model
- Strong experience in Semantic Modeling Metrics Layer design
- Hands-on with Databricks Genie / GenAI-based BI workflows
- Databricks One (Unified BI Experience)
- Prompt Engineering / Instruction tuning for AI systems
- Python (Pandas, PySpark, FastAPI)
- Azure Data Factory (ADF) for ETL pipelines
- Strong SQL and data modeling skills
- Positive to Have
- Cosmos DB / MongoDB (NoSQL concepts)
- Azure Data Explorer (KQL)

Data Stack (Mandatory for Screening)

- Databricks Lakehouse - PySpark, SQL, Delta Lake
- AI for BI - Databricks Genie, Genie Rooms, Instructions, Agents, PowerBI CoPilot
- Semantic Layer - Semantic Models, Metric Views
- ETL Orchestration - Azure Data Factory
- Programming - Python, C#/.NET
- Cloud Platform - Azure (Preferred)
- DevOps - CI/CD Pipelines, Git

📌 Senior Data Engineer (Pune)
🏢 Bajaj Finance
📍 Pune