ABOUT THE AUTHOR
Engineering in context.
I build AI platforms and production AI systems for environments where reliability, security, observability, evaluation, and governance matter as much as model capability.
My work is hands-on and sits at the intersection of software engineering, distributed AI systems, agentic workflows, LLM infrastructure, security, and architecture.
A recurring principle across my projects is keeping critical authority outside probabilistic components:
Models may reason and propose. Trusted software authorizes, constrains, executes, and produces evidence.
I bring more than 22 years of experience in financial services, including Caixa, BTG Pactual, Banco do Brasil, Itaú Unibanco, and ASA SCFI. This background shapes how I approach AI systems operating around sensitive data, financial workflows, regulation, auditability, and operational risk.
Flagship projects
These repositories best represent the architecture and engineering problems I am currently focused on.
Governed LLM Gateway
Provider-neutral LLM execution gateway with policy-constrained model selection, centralized credentials, deterministic ranking, retry/fallback, budgets, provenance, and OpenTelemetry.
Agent Runtime Boundaries Lab
Multi-runtime agent architecture with LangGraph as authoritative workflow owner, Agno/CrewAI specialists behind A2A contracts, durable effect-ledger semantics, crash/retry evidence, cross-runtime OpenTelemetry, and governed model execution.
StateOps
Durable LangGraph state machine with explicit state, parallel investigation, interrupts, Redis checkpointing, restart/resume, replay, forks, idempotent effects, and governed LLM access.
Verifiable AI Governance
Governance control plane for policy, approvals, runtime authorization, enforcement, evidence, assurance, and governed response.
Agentic Security Framework Lab
Framework-neutral agent security across LangGraph, CrewAI, LlamaIndex, and Agno with explicit identity, authorization, human approval, tool boundaries, failure evidence, and MCP.
a2a-otel-kit
Vendor-neutral distributed tracing for A2A agents and MCP services using OpenTelemetry and W3C Trace Context with metadata-only telemetry.
RAGForge
RAG benchmarking and evaluation platform with 10 retrieval configurations, a 230-question Brazilian regulatory dataset, citation evaluation, reproducible experiments, and auditable evidence.