Looking for a job

Thiago Coutinho

@thiagocoutinho

Message

I build production data platforms and agentic RAG systems for fintech and e-commerce.

Brazil

Message

What I'm looking for

I'm looking to expand from production data engineering into AI engineering, building LLM agents and RAG systems with rigorous evaluation, reliable tooling, and measurable outcomes.

Six years building data platforms (Creditas, Loja Integrada, Stone, SmartFit) — Python, Airflow, AWS, Spark, Databricks, Kafka, Snowflake. Sole Data Engineer at Loja Integrada, scaling Kafka/PySpark to billions of daily events; led a SQL Server-to-Snowflake migration at Stone.

At Creditas, I also build AI tooling for the Data Team: a production RAG agent over Confluence, Claude Code subagents for dependency analysis, and a data-validation CLI. Currently migrating that stack to Databricks (Unity Catalog, AI agents).

On evaluation: I built Movie Scout, a recommendation agent where I benchmarked retrieval configs on nDCG and removed cross-encoder reranking after measuring it hurt results — decisions backed by data, not defaults.

Experience

Work history, roles, and key accomplishments

Current

Data Engineer

Current

Creditas

Nov 2024 - Present (1 year 11 months)

Maintains and evolves data pipelines and reliability across financial data workflows, while contributing to AI engineering for the data team. Built an internal agentic tool with Claude Code to map dependencies between SQL Server stored procedures and data warehouse tables, and developed an internal RAG agent over Confluence for data product documentation.

Python Airflow AWS Spark Hudi DuckDB Claude Code LangFlow RAG SQL

Data Engineer

Loja Integrada

Jun 2022 - Oct 2024 (2 years 4 months)

At Loja Integrada (e-commerce marketplace), I worked on large-scale data processing and owned key parts of the data platform.

· Built and maintained ETL pipelines using Python, Airflow, AWS, and Spark
· Implemented Databricks to improve data processing performance and analytics capabilities

Key contributions:

· Designed large-scale ingestion pipelines using Kafka and PySpark, processing billion

Data Engineer

Stone

Jun 2021 - Jun 2022 (1 year)

At Stone, I worked on data platform modernization and migration within a growing data organization.

· Built pipelines integrating multiple data sources across cloud environments
· Supported financial data workflows and reporting

Key project:

· Led the migration of a legacy SQL Server data warehouse to a Snowflake-based lakehouse, improving performance and scalability
· Reverse-engineered busine

Data Engineer

Smart Fit

Feb 2020 - Jun 2021 (1 year 4 months)

· Built ETL pipelines and data workflows using Python, Airflow, Alteryx, and AWS
· Supported analytics and reporting for business teams

Key contribution:

· Re-architected memory-intensive pipelines into in-database processing (Redshift + Airflow), eliminating recurring failures, reducing ~10+ hours/day of manual effort, and improving data delivery reliability