Full-Stack Data Engineer • Multimodal ML Specialist
Juiz de Fora, MG — Brazil
LinkedIn • GitHub • Kaggle • Hugging Face
PhD-trained problem-solver who turns messy, high-volume data into secure, self-service products.
I build cloud-native lake-houses (AWS + Databricks), automate ETL with Python/Selenium bots, fine-tune YOLOv8 + BLIP on EN/PT FrameNet data, and ship Node/React dashboards on PostgreSQL—while holding 99.5% SLAs and delivering 80% manual-effort cuts & 35% cost savings.
| Area | Impact Highlights |
|---|---|
| ETL Automation & Bots | 10+ Python/Selenium templates (retry + alerts) → save 15h/week and trim ops cost 35% |
| Lake-House & Orchestration | 20+ Databricks jobs/day on Delta Lake; dynamic scaling halves failure rates |
| Full-Stack Delivery | AES-256 Node/TS APIs + React/Tailwind portals serving 40 analysts real-time data |
| Multimodal AI | Fine-tuned YOLOv8 + BLIP → +12 BLEU / +9 mAP; models live on HF with Gradio demos |
| GDPR & Security | S3 encryption, RBAC, audit trails; architecture green-lit by C-suite in one review |
| Agile Leadership | 2-week Scrum sprints (Trello/ClickUp) → 20% faster releases; secured budget via ROI-driven roadmaps |
Python · PySpark · SQL · Node/TypeScript · React · PostgreSQL · Databricks · Delta Lake ·
AWS (S3, Lambda, IAM) · Docker · Terraform · YOLOv8 · BLIP · Hugging Face · Power BI · Tableau
| Artemis Smart Data Data Engineer (Full-Stack) 2024-Present |
• Automated 20 + Databricks pipelines/day → 50% fewer failures • Deployed secure Node/TS API + React dashboard for 40 analysts • Cut AWS compute spend 35% via serverless re-design |
| FrameNet Brasil / UFJF ML Researcher 2023-2024 |
• Fine-tuned YOLOv8 & BLIP on EN/PT FrameNet → +12 BLEU / +9 mAP • Published checkpoints on Hugging Face with live Gradio interface |
| Vox Radar Data Scientist 2021-2022 |
• Automated 70% of social-data reporting via Selenium/RPA bots |
- Ph.D. Computational Engineering – UFJF (2018)
Thesis: Discretization-dependent models for excitable media (Phys. Rev. E) - *M.Sc. & B.Sc. Mathematics – UFJF (2013) · UFES (2011)
PT-BR (native) • EN (C1) • ES (B2)
- Email: arroyo.andre@gmail.com
- Phone: +55 (32) 99135-8099
I’m always up for chatting about pipeline automation, lake-house strategy, or multimodal ML. Feel free to reach out!