Luciana
Reynaud Ferreira
AI Platform Governance
LLM FinOps · Observability
Brazil · Remote

I build the control layer that makes AI systems viable in production: observability, cost attribution, model routing, evaluation, and operational guardrails. My focus is turning AI from prototype into accountable infrastructure — measurable performance, clear governance, and economics that hold up under real usage. Today I run that layer at enterprise scale, with a background in production conversational AI for regulated finance. Method: evidence before opinion, metrics before narrative, audit trail before promise.

// Selected Impact
50×
Cost reduction through operating-model redesign and model routing — projected spend reduced from roughly $210 to $4.20/month, with documented headroom for source expansion.
~US$13K/mo
Multi-vendor AI spend under management — 247 seats, 219 users across Claude Enterprise, Claude Team and Cursor — unified into an executive decision layer; ~13% recurring savings identified and selected for industrialization.
1.07M
Users reached in a single WABA broadcast for Recovery at Blip, generating approximately R$2.3M in closed-deal revenue under regulated operating constraints.
44 projects
First company-wide shadow-IT AI inventory: 44 project owners across 12 business units, automated LGPD risk grading mirroring ANPD dosimetry, 5 decisions ratified by the AI Committee.
// Focus
LLM FinOps & Cost Attribution
Token budget design, model routing, batch vs. on-demand cost analysis, and spend visibility across production AI systems.
Observability & Telemetry
Structured logging, per-source instrumentation, tracing, and operational visibility for model-driven systems in production — with OpenTelemetry as the target baseline.
Production Reliability
Deployment architecture, evaluation loops, health surfaces, and monitoring workflows that detect and correct behavioral drift.
AI Governance & Compliance
Risk-aware system design, decision logging, LGPD-aware architecture, and auditability for regulated or high-consequence environments.
// Experience
May 2026 – Present
Brasília · Brazil
AI Governance Analyst II — AI Platform, FinOps & Observability
Gran · edtech, ~800K students
  • Design and ship the systems that move enterprise AI from fragmented experiments to governed, measurable production — discovery, architecture, AI agents, LLM FinOps, MCP governance, and adoption controls.
  • Built an AI FinOps platform unifying multi-vendor telemetry — Claude Enterprise, Claude Team and Cursor: 247 seats, 219 users, ~US$13K/month under management — into an executive decision layer for cost, utilization and license reallocation; identified recurring savings of ~13% of the stack. Selected for industrialization by a dedicated engineering team.
  • Created the company's first shadow-IT inventory of AI applications: 44 project owners across 12 business units, automated LGPD risk grading (3 flags mirroring ANPD penalty dosimetry), 5 decisions ratified by the AI Committee.
  • Led the enterprise search and AI agents rollout end-to-end — SSO access reconciliation (892 directory profiles down to a governed 180-seat group), license lifecycle, heavy-user telemetry, FlexCredits cost controls — activation campaign followed by ~3× monthly assistant usage (≈85K→255K) and ~75% active adoption on Claude Enterprise.
  • Designed a reusable governance blueprint for AI-assisted delivery — security constitution with CWE-mapped rules, CI-based AI code review, pre-commit secret audit, ownership lanes.
  • Run security-gated evaluation of third-party MCP connectors with Cybersecurity and Legal/DPO (Udemy Business homologated; Salesforce piloted under LGPD gate), and designed a two-phase inference credential architecture for key lifecycle, quota isolation and per-team cost attribution.
  • Operationalized AI policy as running systems: policy dispositions computed by a versioned rules engine, and a living AI Risk Register spanning 40+ discovery-and-risk assessments of citizen-built apps.
  • LGPD, ISO/IEC 27001, PCI DSS, DPA and vendor-risk reviews as architecture preconditions for enterprise AI adoption.
Feb 2025 – Apr 2026
Remote · Brazil
AI Systems Engineer
MakeOne Lab
  • Built production observability layer for the lab's LLM stack: per-source structured logging across 52 ingestion endpoints, per-execution ranker run logs with classification tracing, health endpoints, and cost attribution at the token and model level — establishing the instrumentation baseline for future OpenTelemetry integration.
  • Journalism intelligence platform — architecture: Auditable relevance ranking across 52 sources and 150–300 articles/day — each decision traceable to its nearest labeled neighbors, enabling editorial correction without retraining. Built on a hybrid kNN + LLM pipeline anchored in a 280-example labeled dataset.
  • Journalism intelligence platform — serving model and economics: Reduced projected monthly AI spend from roughly $210 to $4.20 — a 50× reduction — by replacing per-user on-demand inference with centralized scheduled processing plus instant dashboard access. Implemented model routing with 99% of classification traffic on the most cost-efficient model tier, maintaining wide headroom for expansion.
  • Journalism intelligence platform — operational visibility: System is debuggable, auditable, and economically predictable rather than prompt-driven and opaque — health endpoints, ranked JSON exports, scraper logs, and per-source execution visibility built in from the start.
  • Sales intelligence pipeline: Built an end-to-end pipeline for transcription, structured extraction, stakeholder and pain-point mapping, enrichment from LinkedIn and company websites, and automated strategic sales report generation. Implemented FastAPI backend, Postgres storage, and dual deployment across Docker and serverless surfaces.
  • Contributed to airport intelligence dashboards on Databricks, supporting real-time analytics for passenger presence and connectivity behavior across multiple airport sites.
Feb 2024 – Feb 2025
Ribeirão Preto · Brazil
Technical Lead
Human Rights Foundation (HRF)
  • Secured and deployed a USD 25,000 grant from the Human Rights Foundation as sole technical lead, designing the full program architecture, curriculum, and technical content for distributed systems and open financial infrastructure.
  • Scaled to 150+ developers across university chapters, delivering protocol-level technical education and establishing structured community formation around systems reasoning.
Jun 2023 – Mar 2024
Remote · Brazil
AI Systems Engineer
Voz AI · independent contractor
  • Embedded LGPD, Central Bank regulations, and KYC requirements as design constraints from the first flow, treating compliance as architecture rather than review-layer overhead.
  • Designed and specified the conversational AI system for BMG Bank: 20 modular Dialogflow CX flows with full error handling, unsupported-format exits, session parameter architecture, and behavioral event tracking defined alongside the data engineering layer.
Nov 2021 – Jun 2023
Remote · Brazil
AI Systems Engineer
Take Blip
  • Owned production customer-facing AI systems for Itaú Personalité, Itaú Credimob, Bradesco Alelo, Recovery, and HDI Seguros across regulated financial and insurance environments.
  • Designed an anti-fraud WABA broadcast to 1,077,000 users for Recovery, generating approximately R$2.3M in closed-deal revenue within LGPD and WhatsApp Business API constraints.
  • Ran iterative model-quality cycles from raw production logs, identifying fallback concentration, low-confidence behavior, and audience-specific vocabulary to inform retraining and system refinement.
  • Designed in-bot NPS, CSAT, and CES measurement flows on WhatsApp and Instagram, instrumenting live systems for continuous quality signal.
// Stack
Core Specialty
LLM FinOps Cost Attribution Model Routing Observability OpenTelemetry AI Governance
Infrastructure & Production
Python FastAPI Docker Linux · Ubuntu Server GitHub Actions Cloudflare Tunnels Postgres Google BigQuery Databricks Distributed Systems
AI & ML
OpenAI API Anthropic API Whisper Hugging Face Vector Search Embeddings RAG Pipelines Pydantic
Compliance & Governance
LGPD GDPR KYC Architecture Drift Detection Decision Logging Evaluation Loops Audit Trails
// Education
2005 – 2011
B.Sc. in Biological Sciences
Federal University of São Carlos (UFSCar)
Scientific method · Statistics · Research design · Systems thinking
// Publications
2026
OTLP on the Wire — Reading the OpenTelemetry Protocol Byte by Byte
Leanpub · Author
Wire-level OpenTelemetry Protocol field guide and laboratory manual
// Contact
Languages — English (native/bilingual) · Portuguese (native)
reynaud.luciana@gmail.com github linkedin medium prumo otlp on the wire
Open to remote