AI Data Engineer | Data Engineering | GenAI | Azure | Databricks | Airflow | Terraform

I'm an AI Data Engineer focused on building scalable data platforms, modern data architectures, and AI-driven applications, combining data engineering with Generative AI and intelligent systems.

Currently pursuing a degree in Computer Science, I design and develop end-to-end solutions — from data ingestion and processing to powering analytics, APIs, and AI applications.

I have hands-on experience with Data Lakes, Lakehouse Architectures, and GenAI systems (RAG & Agents), always prioritizing scalability, performance, and production-ready design.

• 🔹 Build scalable data pipelines (batch and streaming)
• 🔹 Build RAG and agent-based pipelines
• 🔹 Design DataOps and LLMOps environments for AI applications
• 🔹 Design modern data architectures (Medallion, Data Vault, Lakehouse)
• 🔹 Work with distributed processing using Spark/Databricks
• 🔹 Orchestrate workflows with Airflow
• 🔹 Provision infrastructure using Terraform (IaC)
• 🔹 Deliver data for analytics and AI applications
• 🔹 Implement CI/CD for data and AI pipelines
• 🔹 Apply best practices for production-grade data systems

Python • SQL • Spark • Databricks • dbt • Airflow

Azure • AWS • Terraform • Docker • Kubernetes

FastAPI • Pydantic • Pytest • Selenium • Redis

PostgreSQL • SQL Server • Qdrant

LangChain • LLMs (OpenAI / OSS) • RAG Architectures • Vector Databases • Embeddings • Prompt Engineering • AI Agents • LLMOps

Git • GitHub Actions

• 🔹 Experience with modern data stack (Lakehouse + streaming)
• 🔹 Hands-on with GenAI systems (RAG and Agents)
• 🔹 Cloud experience (Azure & AWS)
• 🔹 Infrastructure as Code (Terraform)
• 🔹 Strong integration between data engineering and AI applications
• 🔹 Focus on scalability, reliability, and production-ready systems

• ✉️ Email: lf.nandooliveeira@gmail.com
• 💼 LinkedIn: https://www.linkedin.com/in/luiz-fernando-oliveira-73048918b/