Skip to content
GNU GROUP
Talk to an Engineer
All training programs
FOUNDATIONS → LLMS → RAG → AGENTS → EVALUATE → OPERATE

AI Engineering

Move beyond AI demos into engineered systems: machine-learning fundamentals, LLM applications, retrieval, agents, evaluation, observability, security and production deployment.

Typical duration3–10 days depending on foundation, RAG, agentic and production depth
DeliveryOnline · On-site · Hybrid · AI engineering lab
Practical work7 representative labs
Outcomes
Understand the engineering model behind modern AI applications
Build retrieval-augmented and tool-using systems
Evaluate quality rather than relying on demos
Deploy AI systems with observability, security, reliability and cost awareness
Audience & prerequisites
Who it is for— Software and platform engineers— Developers building AI applications— Architects— Technical leaders evaluating LLM / agent systems— Engineers transitioning into AI engineering
Prerequisites— Basic Python is recommended— Software / API fundamentals helpful— Machine-learning theory is introduced as needed
Representative curriculum

Training topics, organized as engineering modules.

The exact sequence is adjusted to the audience. Foundation topics can be compressed for experienced teams; architecture and troubleshooting can be expanded for advanced programs.

01

AI & Machine Learning Foundations

Understand what models learn and how they are evaluated.

  • AI / ML landscape
  • Supervised and unsupervised learning
  • Training / validation / testing
  • Core metrics
  • Model limitations and failure modes
02

Deep Learning & Transformers

Build the conceptual bridge to modern language models.

  • Neural-network intuition
  • Representations and embeddings
  • Attention
  • Transformer architecture
  • Tokens, context windows and inference
03

LLM Engineering

Treat model usage as a software-engineering problem.

  • Model APIs and providers
  • Prompt and context engineering
  • Structured outputs
  • Function / tool calling
  • Model selection
  • Latency and cost
04

RAG & Retrieval

Ground generation in controlled knowledge sources.

  • Ingestion and chunking
  • Embeddings
  • Vector databases
  • Hybrid retrieval and reranking
  • Grounded generation and citations
  • Retrieval evaluation
05

Agentic AI & MCP

Build multi-step systems that can use tools safely.

  • Agent loops and workflows
  • Tool design
  • Memory patterns
  • MCP concepts
  • Orchestration
  • When multi-agent systems help—and when they do not
06

Evaluation & Observability

Measure quality, reliability and behavior.

  • Evaluation datasets
  • Task and retrieval metrics
  • LLM-as-judge caveats
  • Tracing
  • Regression testing
  • Production feedback loops
07

Production AI / MLOps / LLMOps

Operate AI applications like production software.

  • Deployment patterns
  • Versioning
  • Caching
  • Rate limits and fallbacks
  • Monitoring
  • Cost / performance optimization
08

AI Security & Governance

Control data, tools and model behavior.

  • Prompt injection
  • Sensitive-data exposure
  • Agent / tool permissions
  • RAG trust boundaries
  • Provider and supply-chain risk
  • Guardrails and human oversight
Hands-on work

Labs are part of the learning path.

Exercises emphasize observation, implementation, failure and diagnosis rather than command copying.

01

Build an LLM application with structured output

02

Build and evaluate a RAG pipeline

03

Compare chunking / retrieval strategies

04

Create a tool-using AI agent

05

Expose a tool through an MCP-style interface

06

Trace and evaluate an AI workflow

07

Threat-model an agentic application

Technical visual

See the architecture behind the learning path.

AI Engineering

Production RAG System

See retrieval, reranking, generation and evaluation as one production path rather than a single LLM call.

Production RAG SystemSee retrieval, reranking, generation and evaluation as one production path rather than a single LLM call.01User / AppQuestion02AI GatewayAuth + policy03RetrieverHybrid search04Vector / SearchIndexed knowledge05RerankerTop-k refinement06LLMGrounded generation07Eval + TelemetryQuality • cost • latency
Explore the architecture
AI Engineering

Agentic AI Control Loop

See planning, tool use, memory, policy and evaluation as a controlled loop around the language model.

Agentic AI Control LoopSee planning, tool use, memory, policy and evaluation as a controlled loop around the language model.01User / SystemGoal02Agent RuntimeState + policy03Planner / ModelDecide next step04Tools / MCPExternal actions05MemoryContext + state06Guardrails + EvalCheck + stop
Explore the architecture
CONNECTED PATHS

Turn the learning path into production context.

Explore Knowledge Hub
ConsultingAI Engineering

AI Engineering

Move AI, LLM, RAG and agentic applications from prototype behavior toward measurable, secure and operable production systems.

Continue
Case StudyAI Engineering

Taking a RAG system from demo to production

A representative AI-engineering scenario for a RAG prototype that produces promising demos but lacks measurable retrieval quality, evaluation and production controls.

Continue
ArticleAI Engineering

RAG in Production: Retrieval Is an Engineering System

Why production RAG depends on ingestion, chunking, retrieval, evaluation, security and observability—not only an LLM prompt.

Continue
ConsultingAI Engineering

Security Engineering

Engineering-focused security assessment and hardening across Linux, delivery pipelines, containers, Kubernetes, applications, APIs and AI systems.

Continue
ConsultingDevOps & Platform Engineering

Architecture & Technical Advisory

Independent engineering guidance for organizations making architecture, platform, modernization or technology-selection decisions across connected systems.

Continue
ArticleAI Engineering

Linux Performance Troubleshooting: A Layered Method

A practical workflow for moving from symptoms to evidence across CPU, memory, storage, network and application layers.

Continue
Customization

Align the program to your engineering environment.

Programs can begin with AI fundamentals or focus directly on LLM engineering, RAG, agents, MCP, evaluation, AI security or production AI architecture.

PythonMachine LearningTransformersLLMsEmbeddingsVector databasesRAGMCPAI AgentsEvaluationMLOps / LLMOps
Discuss this program