I'm Vitor Cavalcante, a Senior AI Engineer specializing in LLM systems, Retrieval-Augmented Generation (RAG), and Agentic AI architectures.
I design and deploy production-grade AI systems that combine large language models, vector search, and scalable cloud infrastructure to deliver reliable, explainable, and high-precision AI solutions.
I focus on building intelligent systems that go beyond prompting — architecting full AI pipelines with retrieval, ranking, orchestration, and infrastructure automation.
- Designing high-precision RAG systems with contextual and hybrid retrieval
- Building agentic AI workflows with structured reasoning and tool orchestration
- Optimizing vector search, chunking strategies, and semantic re-ranking
- Engineering AI-ready data pipelines for LLM consumption
- Automating AI infrastructure using Terraform and CI/CD
AI Engineering
- LLMs (GPT-style models)
- Retrieval-Augmented Generation (RAG)
- Agentic AI & Tool-Using Systems
- Prompt Engineering
- Vector Search & Hybrid Retrieval
- Semantic Re-ranking
- LangChain & Structured Output Systems
Backend & APIs
- Python (FastAPI, Pydantic)
- Java (Spring Boot)
- Microservices Architecture
- RESTful APIs
- Data Modeling & Schema Design
Data & Platforms
- Databricks (PySpark)
- SQL
- Data Quality & Observability
- Metadata & Lineage Automation
Cloud & Infrastructure
- Azure (Azure OpenAI, AI Search, AI Foundry)
- AWS
- GCP
- Docker
- Terraform
- CI/CD Pipelines
B.S. in Electrical and Computer Engineering
Minor in Applied Mathematics
GPA 3.9 – Summa Cum Laude
- English (Native)
- Portuguese (Native)
- Spanish (Intermediate)
When I’m not building AI systems, I’m into audio engineering, music production, cooking, and exploring global cuisines.
