🎓 Offline Classroom Training
⌛ 4 Weekends
📍 Pimple Saudagar, Pune
Generative AI for Data Engineering is a 30-hour hands-on program that empowers data professionals to integrate AI into every stage of the data lifecycle. Learn to build self-healing ETL pipelines, automate code generation, parse unstructured data, and deploy AI-powered solutions with real-world labs and a capstone project.
Data Engineers seeking AI-augmented pipelines
Analytics Engineers and Data Analysts
Data Scientists focusing on MLOps
Technical Leaders and Solution Architects
● Data Engineers automating pipelines and integrating AI
● Analytics Engineers working with dbt, Airflow
● Data Analysts seeking task automation
● Data Scientists focusing on MLOps
● Technical Leaders evaluating Gen AI strategies
10+ hands-on projects including:
Data augmentation app with API and frontend
Self-healing ETL pipeline with automated recovery
Text-to-SQL query interface
RAG-powered data assistant with vector databases
Real-time data enrichment service
PDF/document extraction tool
Automated code generator for data pipelines
Capstone: End-to-end Gen AI solution integrating all skills
AI Platforms: OpenAI GPT-4, Claude, Gemini, GitHub Copilot
Frameworks: LangChain, LlamaIndex, Haystack
Vector DBs: Pinecone, Weaviate, Qdrant
Data Stack: Airflow, dbt, Spark, Kafka
Cloud: AWS, Azure, GCP
Dev Tools: Python, SQL, FastAPI, Streamlit, Jupyter
Continuous Assessment (70%):
Module quizzes (20%)
Lab exercises (30%)
Mid-course project (20%)
Final Capstone (30%):
Build end-to-end Gen AI solution
Present to instructors and peers
70% overall score required for certificate
Yes! Designed for working professionals:
Flexible Options:
Part-time: 3 sessions/week, evenings or weekends (2.5-3 hrs each)
Full-time: 5-day intensive bootcamp
Corporate: Custom scheduling
Professional-Friendly:
Immediately applicable skills
Recorded sessions for missed classes
24/7 lab access
8-10 hours/week commitment over 3-4 weeks
80% of participants complete while working full-time
