🇺🇸 English | 🇧🇷 Português
AI Platforms · Agent Runtime · LLM Gateway · MCP/A2A · Evals · LLMOps · Security & Governance
📍 São Paulo, Brazil | 🌍 Open to international opportunities and relocation
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.
These repositories best represent the architecture and engineering problems I am currently focused on.
| Project | What it demonstrates |
|---|---|
| Governed LLM Gateway | Provider-neutral LLM execution gateway with policy-constrained model selection, centralized credentials, deterministic ranking, retry/fallback, budgets, provenance, and OpenTelemetry. |
| Verifiable AI Governance | Governance control plane for policy, approvals, runtime authorization, enforcement, evidence, assurance, and governed response. |
| StateOps | Durable LangGraph state machine with explicit state, parallel investigation, interrupts, Redis checkpointing, restart/resume, replay, forks, idempotent effects, and governed LLM access. |
| 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. |
I am interested in the shared capabilities that allow multiple AI products and teams to run on a common, governed foundation.
flowchart TB
Apps["AI Applications/Agents/Workflows"]
Gateway["Governed LLM Gateway<br/>Execution · Resilience · Provenance"]
Router["Policy Model Router<br/>Authorization · Logical Model Groups"]
Providers["LLM Providers"]
Governance["Governance & Runtime Assurance<br/>Policy · Approval · Evidence"]
Identity["Identity & Tool Access<br/>OAuth/OIDC · MCP · Least Privilege"]
Observability["Observability<br/>OpenTelemetry · A2A · MCP"]
Evaluation["Evaluation & Quality<br/>RAG · Evals · Regression"]
Apps --> Gateway
Gateway -. policy decision .-> Router
Gateway --> Providers
Governance -. constrains .-> Gateway
Identity -. authority boundary .-> Apps
Observability -. traces .-> Apps
Observability -. traces .-> Gateway
Evaluation -. validates .-> Apps
The architecture is intentionally modular. Applications should not need provider credentials, provider-specific retry logic, model-selection rules, or hidden authorization logic scattered throughout their codebases.
A consumer declares its workload and requirements. Platform components determine what it is allowed to use, execute within those limits, and produce evidence about what actually happened.
Explore the broader portfolio architecture →
- Built production AI systems for regulated financial institutions, including conversational and transactional assistants, RAG pipelines, agent workflows, observability, security controls, and governance mechanisms.
- Led enterprise AI adoption for approximately 400 users, including Claude Code for around 250 developers and Claude Enterprise for approximately 150 business users.
- Reduced an investment assistant's average context from approximately 70,000 to 3,000 tokens (~95%) using conditional knowledge retrieval and injection, reducing latency, token consumption, and inference cost.
- Designed semantic routing with intent-specific thresholds, positive and negative examples, ambiguity floors, and margin rules, reaching approximately 94.7% accuracy on its validation dataset.
- Designed engineering controls for enterprise AI adoption including coding-agent guardrails, MCP allowlists, deterministic hooks, architecture rules, auditability, incident procedures, and controlled rollout.
- Translate governance and security requirements into executable mechanisms such as fail-closed authorization, segregation of duties, typed contracts, bounded execution, evidence provenance, and human-controlled high-impact actions.
- Authority is explicit. Model output is not authorization.
- Fail closed when trust is missing. Missing identity, policy, evidence, or configuration must not silently become permission.
- Use the simplest architecture that solves the problem. Agents are not the default answer to every AI workflow.
- Keep deterministic authority around probabilistic reasoning. Models can classify, plan, retrieve, synthesize, and propose without owning every consequential decision.
- Treat identity, tools, providers, retrieved data, and telemetry as trust boundaries.
- Evaluate retrieval and generation independently whenever possible.
- Make evidence inspectable. Model self-report is not runtime proof.
- Minimize telemetry by design. Prompts, responses, credentials, and arbitrary business payloads are not observability defaults.
- Design for retries and re-execution. Idempotency, bounded retries, checkpoints, and explicit failure states matter in agentic systems.
- Document guarantees and non-guarantees. A production-oriented architecture should state what it does not prove.
- Policy Model Router - deterministic, fail-closed authorization and routing across logical model groups.
- MCP Server Auth Template - protected remote MCP server reference using OAuth/OIDC patterns.
- MCP Client Auth Template - matching authenticated MCP client patterns.
- Open Finance BR MCP - Open Finance Brasil/FAPI-BR-oriented MCP reference architecture.
- Controlled Autonomy Lab - experimental comparison of augmented LLMs, chaining, routing, parallelization, evaluator-optimizer, and bounded agents across multiple providers.
- Multi-Agent Credit Desk - auditable multi-agent reference workload for financial workflows.
- Meridian - enterprise knowledge architecture with semantic routing, retrieval-time ACLs, structured queries, DSPy, and grounded answers.
- Alicerce - deterministic execution and evidence-gated engineering loops.
- engineering-loop-schemas - canonical contracts for engineering execution evidence and verdicts.
- Claude Python Engineering Harness - repository-owned rules, hooks, architecture constraints, and quality gates for Claude Code.
- Codex Python Engineering Harness - equivalent engineering harness for Codex-based workflows.
- OpsLens - AWS architecture lab for software-supply-chain intelligence combining deterministic evidence, Bedrock RAG, security, evaluation, IAM, CI/CD, and cost engineering.
- Getnet Multi-Agent Support v2 - spec-driven multi-agent support system originally implemented under a constrained technical challenge.
AI Platforms & Architecture Enterprise AI platforms · model gateways · distributed AI systems · control plane/runtime separation · model routing · provider abstraction · platform capabilities · developer enablement
Generative & Agentic AI LLMs · RAG · LangGraph · durable state machines · multi-agent systems · semantic routing · structured outputs · tool calling · MCP · A2A · DSPy
AI Security & Governance OAuth 2.1 · OIDC · least privilege · fail-closed authorization · tool boundaries · human-in-the-loop · runtime policy · evidence provenance · auditability · prompt-injection authority boundaries
Evaluation, LLMOps & Observability Golden datasets · retrieval evaluation · answer quality · citation support · regression evaluation · OpenTelemetry · W3C Trace Context · OTLP · Datadog · Langfuse · distributed tracing · latency/token/cost observability
Cloud & Platform Engineering AWS · Azure · Amazon Bedrock · Azure OpenAI · Terraform · Docker · Kubernetes · CI/CD · GitHub Actions OIDC · IAM · event-driven systems · observability · cost controls
Technology stack
Languages & backend: Python, FastAPI, Pydantic, TypeScript, Node.js, REST APIs, asynchronous and event-driven systems
AI frameworks & platforms: LangGraph, DSPy, LangChain, LlamaIndex, LiteLLM, Azure OpenAI, Azure AI Foundry, Amazon Bedrock, Anthropic Claude, OpenAI, Gemini
Data & retrieval: Redis Stack, RediSearch, RedisJSON, PostgreSQL, pgvector, OpenSearch, vector search, hybrid retrieval
Observability: OpenTelemetry, OTLP, W3C Trace Context, Datadog, Langfuse, Grafana, Tempo, CloudWatch, structured logging
Engineering: uv, Ruff, Mypy/Pyright strict, Pytest, Bandit, pip-audit, architecture tests, GitHub Actions, Azure DevOps, GitLab CI, Argo CD
My professional background spans corporate banking, credit, treasury, financial operations, software engineering, production AI, enterprise AI adoption, and AI governance.
I have worked with requirements and engineering concerns related to environments governed by frameworks and institutions such as BACEN, CMN, CVM, ANBIMA, LGPD, NIST AI RMF, ISO/IEC 42001, OWASP, MITRE ATLAS, CIS Controls, and NIST security guidance.
This experience strongly influences how I design AI systems: regulation and governance are not documentation layers added after implementation; they become architecture, controls, runtime behavior, and evidence.
Certifications
- AWS Certified AI Practitioner
- AWS Certified Cloud Practitioner
- Microsoft Certified: Azure Fundamentals
- CPA-20 ANBIMA