Overview
A 3-month, weekend-friendly program for engineers moving into data and agentic AI. You’ll go from streaming data into a lakehouse to building agents grounded in that data — with a Databricks certification and open office hours the whole way through.
Delivery: Live Online on Weekends (3 hours) + Open office hours
Curriculum
Module-by-module breakdown
A tentative outline — exact pacing may adjust per cohort.
1
Data Pipelines with Kafka & Flink
- Apache Kafka & Kafka Streams
- Apache Flink for stream processing
- Building production-grade pipelines
2
Data Lakehouse Fundamentals
- Table formats (Iceberg/Delta) and schema evolution
- Ingesting & processing data with PySpark/SQL
- Databricks ecosystem & certification prep
3
Agentic AI & LLM Applications
- Building agents grounded in golden data products
- LLM APIs & GenAI application patterns
- Evaluation & guardrails for agentic workflows
4
Capstone Project & Certification
- End-to-end lakehouse + agent project
- Databricks certification exam
Audience Fit
- Career transition route
- Prior customer-facing/professional experience preferred
- Moving into data & agentic AI engineering
Pre-requisites
- SQL & database concepts
- Programming (Python / Java / Scala) preferred
- Exposure to enterprise data domains or ETL technologies is a big plus
Success Criteria
- Earn a Databricks certification
- Proficiency with table formats
- Ingest/process data in the lakehouse with PySpark/SQL
- Build agents grounded in golden data products
Employment Pathway
- Fast-track into Platformatory
- Startups
- India GCCs
₹36,000 · Limited seats
Ready to get started?
Talk to a coordinator about seats, scholarships, and the next cohort for Data x Agentic AI Immersion.
Talk to a Coordinator