Fundamentals of AI Engineering: Principles and Practical Applications
4h 4mIntermediate2025-06-06
Authors
Vinoo Ganesh
CEO and founder of Stealth Startup
Course details
Transform your software engineering skills into AI engineering capabilities with this in-depth, hands-on course. Learn how to build production-ready AI systems, from embedding generation to model deployment. Master practical implementations of vector stores, RAG systems, and hybrid search while gaining expertise in operational aspects like monitoring and CI/CD. Plus, learn to use GitHub Codespaces to build real-world applications that showcase modern AI engineering practices.
Learning objectives
Build a production ready RAG system using embeddings and vector database pipelines.
Implement monitoring and observability for AI applications using telemetry tools.
Create efficient document processing pipelines with hybrid search capabilities.
Design CI/CD workflows for deploying and testing AI applications.
Optimize AI system performance and costs through caching and resource management.
Learning objectives
Build a production ready RAG system using embeddings and vector database pipelines.
Implement monitoring and observability for AI applications using telemetry tools.
Create efficient document processing pipelines with hybrid search capabilities.
Design CI/CD workflows for deploying and testing AI applications.
Optimize AI system performance and costs through caching and resource management.
Skills covered
Generative AIArtificial Intelligence FoundationsArtificial Intelligence (AI)One-Off
Concepts
0. Introduction
- 01 - Introduction
- 02 - What you should know
- 03 - Course structure
1. AI Engineering
- 04 - What is AI engineering
2. (Local) Large Language Models
- 05 - From deterministic to probabilistic systems
- 06 - Running inference locally
- 07 - Deconstructing the LLM
- 08 - Putting the LLM pipeline together
3. Document Processing
- 09 - Text extraction overview
- 10 - Text extraction fundamentals
- 11 - Document parsing and structure recognition
- 12 - Metadata enrichment and indexing
- 13 - Chunking strategies
4. Embeddings
- 14 - Introduction to embeddings
- 15 - The embedding ecosystem
- 16 - Comparing embedding models
- 17 - Efficient embedding generation
- 18 - Challenge
- 19 - Solution
5. Vector Databases
- 20 - Introduction to vector databases
- 21 - Basic operations
- 22 - Persistence and performance
- 23 - Scaling strategies (approximate nearest neighbor, or ANN)
- 24 - Scaling strategies (caching)
6. Retrieval Engineering
- 25 - Introduction to retrieval engineering
- 26 - Implementing BM25 and vector search
- 27 - Building a hybrid retriever
- 28 - Enhancing retrieval with reranking
- 29 - Building a complete retrieval pipeline
Conclusion
- 30 - Observability
- 31 - Next steps and resources