AI Engineering
An 8-week hands-on course covering RAG pipelines, LLM agents, evaluation frameworks, and production deployment. Live sessions, real codebases, small cohort.
0
Modules
0h
Live instruction
0
Max students
0mo
Recording access
Syllabus
8 modules · 16 hours of live instruction
M1LLM & AI Engineering Foundations
- ✓How modern LLMs work and where they fit in software applications
- ✓Tokens, context windows, temperature and model parameters
- ✓Choosing the right LLM for a use case
- ✓Working with OpenAI and Anthropic APIs
- ✓Prompt design, structured outputs and streaming responses
- ✓Building your first LLM-powered application
M2Reliable LLM Applications
- ✓Designing robust prompts and system instructions
- ✓Structured outputs with JSON and Pydantic
- ✓Function calling and tool invocation
- ✓Conversation state and application memory
- ✓Error handling, retries and fallback strategies
- ✓Building a reliable AI support assistant
M3RAG Foundations
- ✓How RAG works and where retrieval fits into an LLM application
- ✓Document ingestion and preprocessing
- ✓Chunking strategies for different document types
- ✓Embedding models: choosing and evaluating
- ✓Vector stores: FAISS, Pinecone and pgvector
- ✓Building a minimal RAG pipeline end-to-end
- ✓Generating grounded answers with source citations
M4Advanced RAG
- ✓Improving retrieval quality and relevance
- ✓Metadata filtering and hybrid search
- ✓Query rewriting and query transformation
- ✓Reranking retrieved documents
- ✓Handling long documents and complex queries
- ✓RAG failure modes and troubleshooting
- ✓Evaluating retrieval and generated responses
M5AI Agents & Tool Use
- ✓What AI agents are and how they differ from chatbots
- ✓The agent loop: reason, act, observe and repeat
- ✓Function calling and tool design
- ✓Building agents that use APIs and external services
- ✓Agent state, memory and multi-step tasks
- ✓Planning, routing and tool selection
- ✓Building a practical tool-using AI agent
M6LangGraph & MCP
- ✓Building stateful AI workflows with LangGraph
- ✓Nodes, edges, state and conditional routing
- ✓Agent workflows and human-in-the-loop patterns
- ✓Understanding Model Context Protocol (MCP)
- ✓MCP clients, servers, tools, resources and prompts
- ✓Building and connecting an MCP server
- ✓Creating an agent that uses MCP-based tools
M7Evaluation, Observability & AI Security
- ✓Why evaluating AI applications is different from traditional software
- ✓Creating evaluation datasets and golden test cases
- ✓LLM-as-a-judge and automated evaluation
- ✓Measuring retrieval and answer quality
- ✓Tracing AI applications: traces, spans, chains and agent steps
- ✓Monitoring latency, errors and token usage
- ✓Guardrails and responsible AI application design
M8Production AI Engineering
- ✓Designing production-ready AI application architectures
- ✓Building APIs for AI applications with FastAPI
- ✓Testing LLM, RAG and agent applications
- ✓Configuration, secrets and environment management
- ✓Dockerizing an AI application
- ✓Reliability, scalability and cost optimization
- ✓Putting the complete AI application together
- ✓Final capstone: production-style AI Knowledge Agent
Frequently asked questions
Who is this course for?
This course is designed for software developers and engineers who want to build production-ready AI applications. You should have programming experience and be comfortable working with APIs. The course focuses on practical AI Engineering rather than deep ML theory.
What do I need to know before enrolling?
You should be comfortable writing Python and have basic familiarity with APIs, software development, and cloud services. You do not need prior machine learning experience, but a solid software engineering foundation is expected.
What will I build during the course?
You will build practical AI applications using technologies such as RAG, LLMs, agents, and evaluation techniques. The focus is on understanding how to design, build, and improve AI systems that can be used in real-world applications.
How long are the live sessions?
Each live session is 1.5 hours and is held once a week. Optional 30-minute office hours are available after each session for questions, troubleshooting, and guidance.
Are the recordings available after the course ends?
Yes. All live-session recordings and course materials are available to enrolled students for 6 months after the cohort ends, so you can revisit the content and projects at your own pace.
Is this a machine learning or deep learning course?
Not primarily. The course is focused on AI Engineering — building applications around modern LLMs, RAG, agents, APIs, evaluation, and cloud infrastructure. You will learn the ML concepts you need without getting buried in mathematical theory.
Do I need prior AI or machine learning experience?
No. Prior AI or ML experience is not required. However, you should have a solid software development background and be comfortable learning new technical concepts and working with APIs.
Is this course suitable for beginners?
The course is not designed for complete programming beginners. It is aimed at developers and engineers who already know how to build software and want to add practical AI Engineering skills to their toolkit.
What is the refund policy?
You can request a full refund within 7 days of the cohort start date. For refund requests, contact us at [info@auragile.com](mailto:info@auragile.com).
Is this course in English?
Yes. All live sessions, recordings, exercises, and written course materials are provided in English.
Be first to know when it launches
8 weeks · live on zoom/meet · Max 12 students. Register your interest and we'll reach out when the cohort opens.