Professional

1. 2024 — Present

   Ubivis

   Junior data scientist, then data scientist, AI modelling manager, co-owner and CTO, US, in under two years.

   1. Oct 2025 — Present

      Chief Technology Officer, US

      Technology strategy for Ubivis in the United States: the US roadmap for the UbSmart, UbGenius and No-Code AI platforms, on-premise, cloud and hybrid deployments integrated with PLC, SCADA and MES, technical pre-sales across steel, automotive, mining, oil and gas and food, and the US technical team with its MLOps and delivery standards.

      • Strategy
      • Pre-sales
      • Architecture
   2. Dec 2024 — Present

      Owner Associate

      Co-owner of Ubivis in Brazil and the company's commercial lead. I run the commercial work with Scrum and a Kanban board, tracking digital marketing, SEO, applications to innovation funding calls and the execution of expansion strategies. I am also building the US branch: commercial strategy from market mapping to enterprise deals, go-to-market, pricing and positioning with the founder and partners, and demand generation through paid campaigns, e-mail outreach and the company's LinkedIn and Instagram presence.

      • Scrum
      • Kanban
      • SEO
   3. Oct 2024 — Present

      Manager, AI Modelling Team

      Physics-informed and data-driven models for steelmaking and automotive plants, with digital-twin architectures and simulation pipelines tied to PLC, SCADA and MES, with responsibility for budget, vendor choices and ROI models. Built the company's AI governance framework: quality gates, safety checklists and an ethical-use policy, so no model reaches production without review.

      • AI governance
      • MLOps
   4. May — Oct 2024

      Data Scientist, AI

      Physics-informed models for steelmaking and automated feature pipelines for industrial time series. Promoted from junior after three months.

      • PINNs
      • tsfresh
      • Polars
   5. Feb — May 2024

      Junior Data Scientist, AI

      Machine-learning models and data pipelines for industrial applications, with research in process optimization, anomaly detection and sensor data analysis.

      • Anomaly detection
      • Feature engineering
2. Sep 2023 — Nov 2024

   AI Resident · SENAI Hub of AI

   Physics-grounded neural networks for steelmaking efficiency and computer vision segmentation of urban soil for smart cities.

   • PyTorch
   • Computer vision
3. Jun 2019 — Jan 2021

   Collaborator, Specialized Services in Applied Nuclear, Atomic and Molecular Physics · UEL

   University extension project at the Applied Nuclear Physics Laboratory (LFNA), coordinated by Prof. Dr. Avacir Casanova Andrello: X-ray micro-computed tomography services, from preparing samples of many kinds to image reconstruction, 2D and 3D analysis and data analysis (100 hours).

   • Micro-CT
   • 3D reconstruction
   • Data analysis
4. 2019 — 2025

   Technical translator and reviewer, English and Portuguese · Self-employed

   Scientific articles, mostly in civil engineering, physics and biology, for university researchers.

Selected work

• Rare-event defect detection in robotic welding

  A binary classifier for defects that almost never happen, trained on extremely imbalanced sensor data with 700+ time-series features per weld cycle. It runs end to end, from acquisition to a containerized deployment. The project, delivered by Ubivis, was a Top 3 finalist of the FINEP Innovation Award 2025 (Digital Transformation of Industry).

  • Time series
  • tsfresh
  • Imbalanced learning

• Physics-informed models for steelmaking

  Neural networks that combine process physics with plant data for basic oxygen and electric arc furnaces, where data alone does not cover the operating range.

  • PINNs
  • PyTorch
  • Process modelling

• ML pipelines over 170 GB of sensor data

  Polars with Zstandard-compressed Parquet, disk caching, adaptive undersampling with MiniBatchKMeans and parallel feature extraction, sized to run on a single machine.

  • Polars
  • Parquet
  • Data engineering

• Rust back end for the Ubivis platform

  The Rust rewrite of the platform's back end, which I develop: a hexagonal workspace of 26 crates with a GraphQL API, NATS JetStream events, Cerbos authorization and OpenBao secrets, plus retrieval-augmented generation (RAG) and Model Context Protocol (MCP) servers for AI agents.

  • Rust
  • RAG
  • MCP

Talks

1. Sep 2026

   Peer-reviewed paper and talk · ROG.e 2026, Rio de Janeiro

   Impact of Applying Artificial Intelligence Techniques in Risk-Based Inspection for Equipment in Oil Refining Units, presented in a technical session on September 24.

2. 2025

   Stage presenter for Ubivis · GITEX Europe, Berlin

   Presented Ubivis's industrial AI platform to a global audience.

Tools

1. Leadership

   Technology management · Technology pre-sales · IT strategy · AI governance · Scrum · Kanban

2. ML

   PyTorch · scikit-learn · XGBoost · LightGBM · TensorFlow

3. Data

   Polars · Pandas · tsfresh · NumPy · SciPy · SQL

4. MLOps

   Docker · Kubernetes · GCP · MLflow · Airflow · FastAPI · CI/CD

5. Industry

   PLC · SCADA · MES · OPC UA