NBO Platform on Vertex AI
Owned the integration patterns, security controls, and MLOps review gates that moved multi-channel next-best-offer journeys from pilot to production.
Senior AI Solutions Architect / Principal Data Scientist
Bruno Vilela Quirino
I design and govern enterprise-grade GenAI and ML platforms that power personalization and decisioning at scale. Hands-on with reinforcement learning (contextual bandits, Q-learning), recommendation systems (NBO), and MLOps on Vertex AI, with multi-cloud experience (GCP, Azure, AWS).
Guitar, mountain biking, and travel.
Professional Summary
Architecting responsible AI platforms
I'm a senior AI solutions architect focused on building and governing GenAI/ML platforms for aviation and adjacent domains. My work combines advanced modeling and reinforcement learning with architecture governance, integration blueprints, privacy-by-design, and reliable MLOps. I partner with engineering and product to translate strategy into scalable systems, ensuring experimentation discipline (A/B testing, DoE), observability, and measurable business impact.
Featured Work
Impact highlights
RL for Personalization
Delivered contextual bandits and Q-learning services via APIs, pairing RL policies with GenAI-assisted template suggestions for dynamic campaigns.
Architecture Governance
Defined standards, review gates, and cost/performance trade-offs aligned with well-architected principles covering reliability, security, cost, performance, and operations.
Cross-Functional Delivery
Partnered with engineering, product, and commercial teams to link platform capabilities to customer experience and revenue outcomes.
Selected Experience
Building AI platforms end-to-end
LATAM Airlines
Senior Data Scientist / AI Solutions Architect- Owned NBO platform architecture on GCP Vertex AI; acted as design authority across squads.
- Built uplift modeling pipelines powering ancillary upsell and lifecycle marketing triggers.
- Designed and deployed multi-armed bandit services for experimentation and journey orchestration, using GenAI assistance to craft template variants from bandit context.
- Delivered product recommendation engines (collaborative filtering, content-based) integrated with personalization APIs.
- Developed customer lifetime value segmentation and monitoring dashboards linked to commercial planning.
- Led architecture reviews, privacy controls, and MLOps standards (CI/CD, registry, monitoring) to reduce time-to-production risk.
Kumulus
Senior Data Scientist- Delivered RAG pipelines and GenAI chatbots spanning web and WhatsApp, covering document understanding, demand forecasting, and computer vision briefs.
- Applied contextual bandits and reinforcement learning to guide chatbot flows and conversion prompts against user-specific variables.
- Orchestrated Databricks/Spark ETLs with Azure/AWS integrations, leveraging LangChain retrieval workflows and production observability.
Plusoft
Data Scientist- Executed large-scale segmentation (LTV, churn tendencies), geomarketing, and time-series models.
- Implemented PySpark pipelines for data quality, modeling, dashboards, and API integrations.
Vertem
Data Scientist- Developed anti-fraud risk modeling, segmentation, and CLV initiatives with Azure/MLflow MLOps.
- Drove stakeholder storytelling and model monitoring practices.
Earlier Full-Stack Engineering (Intern/Junior)
- Built full-stack web apps using PHP (Laravel/CodeIgniter), MVC, JavaScript/jQuery, HTML/CSS/Bootstrap.
- Delivered REST APIs, Docker setups, and foundational CI/CD for modular microservices.
Skills
Architectural and scientific toolkit
Platforms & Governance
- Cloud & Platforms: GCP Vertex AI; Azure (Data/AI); AWS
- Architecture & Governance: Microservices; Event-Driven; API-First; Architecture Reviews; Well-Architected; Privacy-by-Design; C4/UML
Data & MLOps
- Data & AI: Reinforcement Learning (contextual bandits, Q-learning); Recommenders (NBO); RAG/Embeddings; Vector DB; Feature Stores; Observability
- MLOps & DevSecOps: CI/CD for ML; Model Registry; Lineage; Monitoring & Drift; IaC
Integration & Analytics
- Web & Integration: REST APIs; PHP (Laravel/CodeIgniter), MVC; JavaScript/jQuery; HTML/CSS/Bootstrap; Docker
- Analytics: Causal inference; A/B testing & DoE; Time series; Clustering; Interpretable linear/logistic models
Recognition
Awards & Certifications
Awards
- Data Science Game 2018 - 4th place
- Data Mining Cup 2022 - 4th place
- ITA - LATAM Data Science Challenge 2023
- KDD-BR 2018 (Brazilian KDD competition)
Certifications
- Azure Fundamentals; Azure AI-900
- Oracle AI
- Databricks Data Scientist
- GCP Vertex AI
- AWS SageMaker
Projects
Open source & research
COSMIC - Python package for magnetic turbulence analysis
RepositoryA reusable library inspired by ESA Cluster mission data. Originated from an undergraduate thesis and now released as a tested, reusable package with a clear API for professional portfolios.
Key features
- Ingestion and preprocessing for .dat and CEF files, consolidating the logic from original notebooks.
- Current density and gradients via the curlometer method.
- Turbulence metrics: PVI, magnetic volatility, Gaussian-kernel smoothing.
- Robust time-series cleaning and normalization: outlier detection, magnetic energy, and one-line resampling utilities.
- Spectral diagnostics: total/parallel/perpendicular PSD, temporal and spatial correlations, high-order structure functions.
- MVA, multi-point timing analysis, field-line curvature estimation, helicity, tetrahedron quality factors.
- Extreme value analysis tools: POT, declustering, and associated visualizations.
- Automated tests with pytest for reproducible results.
- Patent held by the author.
MarkowitzPortfolioOPT
RepositoryProduction-oriented implementation and backtesting utilities for portfolio optimization with Brazilian equities.
DMC20
RepositoryData Mining Cup solution pipeline; documented approach and experiments.
whatsthis
RepositoryChrome extension to fetch WhatsApp messages by number.
getIgId
RepositoryMinimal API to retrieve Instagram user IDs.
HashCode problems
Documented solutions with complexity notes and heuristic strategies.
Selected repositories: morepizza_hashcode, hashcodeDataCenterOptimization, adventofcode20.
Blog
Recent writing
DMC 2022: SVD x Markov Chain
Shows how combining SVD-based user and category similarity with Markov chains forecast weekly repeat purchases for DataMiningCup 2022, using Bayesian tuning to hit 92% accuracy within hardware limits.
Identifying Extreme Events with the Dragon-King Test
A practical walkthrough on detecting heavy-tail anomalies; statistical assumptions, implementation notes, operational caveats, and visualization tips.
Captcha Solver
End-to-end pipeline for CAPTCHA solving: data collection, augmentation, model training, evaluation trade-offs (accuracy vs. latency), and deployment considerations.
Contact
Let's collaborate
For speaking, collaboration, or advisory requests, please reach out via the form or connect on LinkedIn. I'm open to high-impact projects in GenAI platforms, personalization, and architecture governance.