AI Engineer building production-oriented ML systems for agribusiness, one of the most data-rich and underserved verticals for applied AI globally. Work spans multi-agent RAG orchestration, on-device computer vision, and end-to-end NLP pipelines with Transformer fine-tuning.
Open to remote ML/AI engineering roles — international or Brazil-based.
| Project | What it solves | Stack |
|---|---|---|
| sb100_agents | Producers have no scalable access to precise agronomic knowledge, agronomists are costly and research literature is inaccessible at field level | Python · LangGraph · Qdrant · HuggingFace |
| visiosoil-app | Soil texture assessment requires lab analysis or trained specialists, neither is viable for large properties in low-connectivity rural environments | Flutter · Dart · TFLite · Riverpod |
| tweet-sentiment-analysis | Generic sentiment classifiers fail on social media language, slang, sarcasm and platform-specific syntax cause unreliable outputs | Python · HuggingFace · FastAPI · Docker |



