02 · Curriculum
What's in the course.
- Lakehouses, Semantic Layers, and AI-Ready Data Platforms120m
Intermediate
The Modern Data Engineering Playbook
Data engineering has never been more consequential. The rise of LLMs, RAG systems, and AI-native applications hasn't made pipelines less important; it's made them the foundation on which everything else depends. Across four intensive, hand…
- 172+
- enrolled
- 10 hrs
- of instruction
- 8
- lectures
- 4
- modules
Taught by Sachin Tripathi and Abhishek Kumar01 · What you'll be able to do
Five things you can ship afterwards.
Data engineering has never been more consequential. The rise of LLMs, RAG systems, and AI-native applications hasn't made pipelines less important; it's made them the foundation on which everything else depends. Across four intensive, hands-on workshops, you'll rebuild your understanding of the data stack from the ground up. Lakehouse architecture, semantic layers, DataOps practices like CI/CD and observability, and the full pipeline behind real AI systems: RAG ingestion, embedding lifecycles, and vector store delivery. You'll also learn what happens after you ship. How to instrument LLM pipelines, catch dataset drift and prompt regressions before they become incidents, and build feedback loops that make your systems smarter over time. Whether you're a data engineer stepping into AI or a seasoned practitioner modernising your stack, this course gives you the blueprints to build data infrastructure that's reliable, observable, and ready for the AI era.
Design and implement
Design and implement a modern lakehouse architecture using Delta Lake, with semantic layers that make data accessible, trustworthy, and ready for both analytics and AI workloads.
Apply DataOps principles
Apply DataOps principles to build reliable, observable data pipelines with CI/CD, automated testing, data quality checks, and lineage tracking using orchestration tools.
Build end-to-end data pipelines
Build end-to-end data pipelines that power AI systems, covering RAG ingestion, embedding generation, vector store delivery, and knowledge base management.
Instrument and monitor production
Instrument and monitor production LLM pipelines using tools like LangSmith and Weights & Biases, tracking prompt telemetry, retrieval accuracy, and embedding quality across the full stack.
Build automated feedback loops
Build automated feedback loops that detect dataset drift, prompt regressions, and retrieval degradation, keeping AI systems reliable and continuously improving long after deployment.
03 · Instructors
Taught by the people who built it.
Sachin Tripathi
All courses by SachinAbhishek Kumar
All courses by Abhishek04 · Is it for you?
Who it's for, and what to bring.
Built for
- Data Engineers looking to modernise their stack and build infrastructure that supports AI and ML workloads.
- Analytics Engineers who want to go beyond transformation layers and understand the full data platform picture.
- ML Engineers who work at the intersection of data pipelines and model deployment and want stronger data engineering foundations.
- Data Architects designing scalable, AI-ready platforms for their organisations.
- DataOps / Platform Engineers responsible for pipeline reliability, observability, and operational excellence.
- Senior Data Scientists / Forward Deployed Engineers transitioning into more engineering-heavy roles and looking to upskil in modern data infrastructure.
Bring with you
- Data Platforms & Storage - Databricks or Snowflake (trial/free accounts suffice), Delta Lake, and Apache Iceberg.
- Processing & Orchestration - Apache Spark for data processing, and pipeline orchestration.
- AI & Vector Infrastructure - OpenAI APIs (or equivalent), and a vector database (Pinecone or Weaviate).
- Observability & Experiment Tracking - LangSmith and Weights & Biases for monitoring and evaluating LLM pipelines.
- Development Setup - VS Code or any equivalent IDE, GitHub or GitLab for version control and CI/CD, and Docker (optional but recommended).
Next step · Prove it
This course prepares you for the ACDE credential.
The ADaSci Certified Data Engineer (ACDE) exam tests the skills this course teaches. Members sit it at a discount.
05 · FAQ
Before you enrol.
Each of the 4 modules is a recorded live session, with the GitHub repo, slide deck and handouts from that session. Watch at your own pace.
$199.00
Related credentials
ADaSci Certified Data Engineer (ACDE)
The ADaSci Certified Data Engineer program is a 30-hour self-paced online certification designed to build practical expertise in modern data engineering. It offers end-to-end training in designing scalable data pipelines, managing cloud infrastructure, and ensuring data quality and governance.
The Chartered Data Scientist (CDS™) Designation
Achieve the highest distinction in the data science profession.
Keep going
Next on the Data platform engineer path.
Ready to start?
$199, or free with Premium membership.