AI & Data Engineer
I build AI agents, data platforms, and the systems that connect them.
Brasília, Brazil
Trajectory
I am an AI & Data Engineer based in Brasília, Brazil. I build agents and the execution, evaluation, data, and cloud systems behind them.
The path started in electronics and IT, then applied machine learning and data science. I later set technical direction across data platform teams, supported shared lakehouse and orchestration capabilities, and worked on a Spark-to-Kubernetes migration that improved infrastructure efficiency.
That platform work now sits under agent systems: production harnesses, durable delivery runtimes, and multi-agent workflows with human gates and inspectable evidence. I treat an agent as a governed software system, not a prompt with a model behind it.
Experience
Professional work described by the problem space and the result. Each case study separates my contribution from shared team delivery.
All workAgent runtime engineering
ContributionI evolved the Pi-based runtime and built major parts of its persistent execution, recovery, tracing, feedback, and evaluation systems.
DeliveredPi-based production harness
Read case studyDurable software delivery
ContributionI designed the system and implemented its custom graph, durable runtime, execution controls, human gates, validation path, and evidence-based delivery workflow.
DeliveredCustom durable agent runtime
Read case studyMulti-agent orchestration
ContributionI designed and built the platform end to end, including the agent contracts, workflow state machine, verification gates, worktree isolation, persistence, API, and operational interface.
DeliveredArtifact-gated agent delivery
Read case studyData platform engineering
ContributionI designed and implemented the core execution platform and operator, and co-designed or led the shared libraries and declarative orchestration tools.
DeliveredData platform modernization
Read case studyAnalytics cost optimization
ContributionI implemented the optimization process across query behavior, physical table design, capacity, retention, and storage placement.
Delivered25% lower monthly BigQuery cost
Read case studyPublic projects
Agent workflows, Spark orchestration, and change data capture. Public repositories with implementation notes.
All projectsGive autonomous coding agents a clear goal and a reliable way to know when they are done. Includes templates and worked examples.
Run Spark jobs on Kubernetes from Airflow, with a custom operator, working deployment examples, and Google Cloud Storage integration.
Stream MySQL changes through Kafka and Debezium on Kubernetes. Includes connector configuration and a FastAPI consumer you can run.
Contact
For a role, collaboration, or a concrete engineering problem, start with a short note. Email is the fastest path.