Projects

Named case studies from courts, agencies, and production AI programs.

These are institutional case studies: real programs, real constraints, and delivery choices that had to survive beyond a demo.

Project Legal TechPublic Sector AI

CNJ / PNUD

PEDRO Precedent Discovery Platform

Data Scientist · Jul 2022 - May 2023

National-scale precedent discovery initiative for CNJ and PNUD, combining FastAPI services, unsupervised NLP, semantic grouping, and governed experimentation to systematize qualified precedents from Brazil's highest courts.

Primary impact

Enabled discovery of more than 30 precedent categories across long-form judicial decisions.

  • FastAPI
  • NLP
  • Semantic Similarity
  • MLflow
  • Legal Tech

Outcomes

  • More than 30 precedent categories identified through semantic workflows
  • AI services integrated with CNJ systems through REST APIs
Read project
Project Legal TechPublic Sector AI

PGDF

OSIRIS Legal-Fiscal AI Workflows

Data Scientist · May 2023 - May 2024

AI delivery for PGDF legal-fiscal operations, spanning production APIs, supervised and semi-supervised models, active learning, and early LLM exploration for document-heavy institutional workflows.

Primary impact

Brought governed ML workflows and production APIs into legal-fiscal operations, while designing active-learning paths for longer-term model adaptation.

  • FastAPI
  • Active Learning
  • MLflow
  • DVC
  • LLM

Outcomes

  • Production APIs connected model outputs to PGDF internal systems
  • Active-learning loop designed to reduce model drift over time
Read project
Project Legal TechPublic Sector AI

TST

SABIA Bem-Te-Vi LLML Research

AI Research Team Lead · May 2023 - May 2024

Strategic R and D work for the Superior Labor Court focused on evolving the Bem-Te-Vi platform with unsupervised NLP, clustering workflows, and Long Life Machine Learning patterns designed for continuous adaptation.

Primary impact

Introduced unsupervised NLP and an early Long Life Machine Learning loop to support jurisprudence analysis, process clustering, and future feedback-driven adaptation inside the Bem-Te-Vi platform.

  • NLP
  • LLML
  • Transformers
  • Clustering
  • Research AI

Outcomes

  • Functional unsupervised NLP pipelines delivered for clustering and exploration of legal case data
  • Prototype LLML workflow validated to support future feedback-driven model updates
Read project
Project Legal TechPublic Sector AI

TRF1

ALEI TRF1 Legal Analysis Platform

Data Scientist & Backend Developer · Mar 2021 - Jul 2022

AI-driven initiative for TRF1 that brought together backend delivery, unsupervised machine learning, ETL, and court-staff enablement to improve legal analysis and case-management workflows.

Primary impact

Combined backend architecture, unsupervised ML, and hands-on institutional enablement to support legal analysis and improve case-management workflows for second-instance chambers at TRF1.

  • FastAPI
  • Flask
  • NLP
  • Backend
  • Legal Tech

Outcomes

  • Hybrid AI and backend team led across implementation, coordination, and delivery
  • Semi-automated data-analysis pipeline built to reduce manual workload
Read project