Rodrigo Ribeiro | Senior Data Engineer — Text to SQL with LLMs, Apache Spark, dbt, ClickHouse, Python, Azure

LLM Ollama qwen2.5-coder Python sqlglot Streamlit MySQL 8 Docker pytest LLM Evaluation

mytext2sql architecture: Streamlit UI, pipeline with prompts, Ollama LLM, sqlglot SQL guard and read only executor with retry loop, MySQL semantic views over raw tables, and four defense layers

76.7%23/30

2/2

1.07

28.5s

		%
	10/13	77%
	10/12	83%
	3/5	60%

Apache Spark PySpark Docker MySQL Parquet SCD Type 2 Star Schema Airflow

Airbyte OSS ClickHouse dbt MySQL Docker Bronze / Silver / Gold MergeTree Engine Shell

📊 Power BI Portfolio

Power BI DAX Data Visualization Business Intelligence

Skills

Senior Data Engineer specializing in Text to SQL, Large Language Models, Generative AI for analytics, Ollama, local LLMs, qwen2.5-coder, prompt engineering, LLM evaluation, sqlglot, Streamlit, semantic layer, Apache Spark, PySpark, dbt, dbt-core, dbt-clickhouse, ClickHouse, Python, Airflow, Snowflake, Azure, AWS, SQL Server, MySQL, FastAPI, Docker, Power BI, DAX, Medallion Architecture, Lakehouse, ETL, ELT, Data Warehouse, Star Schema, SCD Type 2, Iceberg, Parquet, SSIS, Azure DevOps, Airbyte, Agile, Scrum, SAFe. Open to remote work, relocation, and visa sponsorship opportunities in the United States, Canada, Europe, and globally. Engenheiro de Dados Sênior com mais de 25 anos de experiência em pipelines de dados, arquitetura lakehouse, modern data stack e IA generativa aplicada a dados (Text to SQL com LLM local).

Featured project: mytext2sql, natural language to SQL with a local LLM on Ollama, semantic views, two layer SQL security (sqlglot validation and read only database user), automatic retries, Streamlit interface and automated evaluation with 30 gold SQL questions comparing execution results.

Education: Postgraduate Specialization in Data Science and Machine Learning (Anhanguera Educacional, in progress). Postgraduate Specialization in Project Management (Senac Brasil). Bachelor's Degree in Computer Science. Pós-graduação Lato Sensu em Ciência de Dados e Machine Learning. Pós-graduação Lato Sensu em Gerenciamento de Projetos.

Certifications: Microsoft Certified Azure Database Administrator Associate DP-300, Microsoft Certified Power BI Data Analyst Associate PL-300, Microsoft Certified Azure Data Engineer Associate DP-203.

Currently employed at Dell Technologies as Senior Data Engineer in Florianópolis, Santa Catarina, Brazil. Available for L-1 intracompany transfer or direct sponsorship.