Visão Geral

Este curso capacita desenvolvedores a criar aplicações utilizando Inteligência Artificial Generativa e Large Language Models (LLMs). O participante aprenderá os fundamentos técnicos dos modelos generativos, integração com APIs de IA, técnicas de prompt engineering, arquiteturas modernas como RAG (Retrieval-Augmented Generation), desenvolvimento de agentes inteligentes e boas práticas para construção de aplicações corporativas baseadas em IA Generativa.

Objetivo

Após realizar este curso, você será capaz de:

• Compreender a arquitetura e o funcionamento dos modelos generativos modernos
• Integrar aplicações com APIs de Large Language Models (LLMs)
• Desenvolver prompts avançados para aplicações corporativas
• Implementar soluções utilizando RAG e bases de conhecimento corporativas
• Criar agentes inteligentes para automação de processos e tomada de decisões
• Aplicar boas práticas de segurança, governança e observabilidade em aplicações de IA Generativa

Publico Alvo

• Desenvolvedores de software
• Engenheiros de software
• Engenheiros de Machine Learning
• Arquitetos de soluções
• Profissionais DevOps e Platform Engineering
• Profissionais de tecnologia interessados em desenvolvimento com IA Generativa

Pre-Requisitos

• Conhecimentos de programação (preferencialmente Python ou JavaScript)
• Familiaridade com APIs e desenvolvimento de aplicações web
• Conhecimentos básicos de bancos de dados e arquitetura de software
• Interesse em Inteligência Artificial Generativa

Materiais

Conteúdo Programatico

Module 1: Introduction to Generative AI Development

1. Overview of Generative AI technologies
2. LLM ecosystem and architecture
3. Developer use cases and opportunities
4. Foundation models overview
5. Generative AI development lifecycle
6. Enterprise AI application scenarios

Module 2: Large Language Models Fundamentals

1. Transformer architecture overview
2. Tokens and embeddings
3. Context windows and attention mechanisms
4. Model capabilities and limitations
5. Inference concepts
6. Open-source and commercial LLMs

Module 3: Working with Generative AI APIs

1. API integration fundamentals
2. Authentication and security
3. Request and response handling
4. Structured outputs
5. Function calling concepts
6. Error handling and resiliency

Module 4: Prompt Engineering for Developers

1. Prompt design principles
2. Zero-shot and few-shot prompting
3. Chain-of-thought techniques
4. Context management strategies
5. Prompt optimization and evaluation
6. Prompt templates and reusable patterns

Module 5: Building AI-Powered Applications

1. Application architecture patterns
2. Chat-based applications
3. Content generation solutions
4. AI-powered search experiences
5. Workflow automation applications
6. User experience considerations

Module 6: Embeddings and Vector Databases

1. Embedding concepts
2. Semantic search fundamentals
3. Vector databases overview
4. Similarity search techniques
5. Indexing and retrieval strategies
6. Knowledge representation approaches

Module 7: Retrieval-Augmented Generation (RAG)

1. RAG architecture fundamentals
2. Document ingestion pipelines
3. Retrieval strategies
4. Context enrichment techniques
5. Enterprise knowledge integration
6. RAG optimization best practices

Module 8: AI Agents and Autonomous Workflows

1. Introduction to AI agents
2. Agent architectures and patterns
3. Tool usage and orchestration
4. Multi-agent systems overview
5. Autonomous workflows
6. Enterprise automation use cases

Module 9: Security, Governance and Responsible AI

1. AI application security
2. Data privacy and protection
3. Prompt injection risks
4. Model misuse prevention
5. Responsible AI principles
6. Governance and compliance requirements

Module 10: Observability and Performance Optimization

1. Monitoring AI applications
2. Evaluating model outputs
3. Cost optimization strategies
4. Latency and scalability considerations
5. Reliability engineering practices
6. AI operations fundamentals

Module 11: Enterprise Integration and Deployment

1. Integrating with enterprise systems
2. Cloud deployment architectures
3. CI/CD for AI applications
4. MLOps and LLMOps concepts
5. Production readiness practices
6. Operational governance

Module 12: Capstone Project and Real-World Scenarios

1. End-to-end Generative AI application development
2. RAG implementation project
3. Agent-based workflow automation
4. Security and governance validation
5. Performance optimization exercises
6. Final enterprise Generative AI solution project