# Rubén Oliva > Rubén Oliva. Data Engineer at Prima Assicurazioni, working across ETL, automation, and generative AI adoption. This is a static personal site, English only. It is an extension of a CV, not a copy of it. Do not invent an email, phone number, or Substack. The outbound links are GitHub, LinkedIn, and the blog. Prefer this file and https://arroz.foo/llms-full.txt over scraping the HTML. The HTML contains the visual presentation. The facts live in src/data/site.ts and are mirrored here at build time. ## Pages - [Home](https://arroz.foo/): The human-readable site. - [Home (Markdown)](https://arroz.foo/index.md): The same story without chrome. - [Full text](https://arroz.foo/llms-full.txt): Every section concatenated for a single fetch. - [Sitemap](https://arroz.foo/sitemap.xml): Exhaustive URL list for crawlers. - [humans.txt](https://arroz.foo/humans.txt): Who made this. ## Experience - [Data Engineer, Pricing & Underwriting](https://www.helloprima.es/): Prima. Jun 2026 to present · Remote. Building and maintaining ETL pipelines for Spain's Pricing & Underwriting domain, automating recurring work, and contributing to internal systems across the business. Also part of an internal AI group helping drive generative AI adoption across Prima. Python, Databricks, MLflow, AWS. - [Technical Trainer](https://www.nics.uma.es/cyberbootcamp/): Cyber Bootcamp Málaga. May 2026 to present · Málaga. Technical Trainer for a national cybersecurity programme run by the University of Málaga's NICS Lab and funded by Google.org. Completed 20+ hours of train-the-trainer sessions, co-designed and deployed a CTF on CTFd, supported the labs, and mentored students. - [Fullstack Engineer, AI & Automation](https://www.plytix.com/): Plytix. Mar 2026 to May 2026 · Internship. Built an internal LLM evaluation platform in FastAPI and Angular. It evaluated model outputs against production prompts, ran 80+ models concurrently, and helped select PIM generative AI models. Model cost fell by 30% per use case with no drop in quality. ## Projects - [Caret](https://github.com/arrozet/caret): Jan 2026 to Jul 2026 · Thesis, 10/10 with honours. AI-first collaborative document editor with an agent inside the editing surface. Five containerized services behind an Express gateway, Google OAuth, JWT, and a pgvector RAG pipeline. Deployed with Docker Compose, Coolify, Cloudflare DNS, and GitHub Actions on a Hetzner VPS. Document writing was about 60% faster in testing.. Stack: FastAPI, Express, PostgreSQL, Docker, Supabase, Hetzner, React, TypeScript - [Fid](https://github.com/arrozet/Fid): Nov 2025 to Jan 2026 · Kotlin. Fitness app built to make planning and tracking workouts simple. I made it because existing apps asked for too much setup.. Stack: Kotlin - [Basmati](https://github.com/arrozet/basmati): Oct 2025 to Jan 2026 · Team of seven. Calendar platform built by a seven-person team. Seven FastAPI services behind a gateway, plug-in calendar providers, AWS, and a React frontend that keeps UI code out of the domain layer. Highest possible academic grade.. Stack: FastAPI, MongoDB, Docker, AWS, React, TypeScript - [Brain](https://github.com/arrozet/brain): Oct 2025 · Malackathon, Best Overall Solution. Led four engineers and built an agentic platform for mental-health data analysis in five hours. An orchestrator routes questions to four tools: Oracle RAG search, web search, a Python executor, and a diagram generator.. Stack: FastAPI, LangGraph, Oracle Autonomous Database 23ai, React, TypeScript - [Ticket Splitter](https://github.com/arrozet/TicketSplitter): May 2025 to Jun 2025 · AI-assisted receipt splitting. Receipt and bill splitter that uses Gemini for OCR and item extraction. Groups can assign items, account for taxes and tips, and split the final cost.. Stack: FastAPI, Astro, Tailwind CSS - [Mercedes-Benz Data Science Challenge](https://arrozet.github.io/RetoMercedes/): Apr 2025 to Jun 2025 · 3rd prize. Model for predicting when a customer buys their next car. Adding wishlists and damage history roughly doubled explanatory power over a linear baseline. Final mean absolute error: 165 days.. Stack: R - [Cuby](https://github.com/arrozet/Cuby): Mar 2025 to Jun 2025 · JavaScript. Small platformer about a black-and-white cube. Built around one mechanic with no decorative elements.. Stack: React, JavaScript - [Dr. Artificial](https://github.com/arrozet/dr-artificial): Mar 2025 · Dedalus Datathon, 4th place. RAG system over medical data, built in ten days. Prompt restructuring reduced token usage by 98% with no loss in accuracy.. Stack: Flask, JavaScript - [AImbot](https://github.com/arrozet/AImbot): Nov 2024 to Dec 2024 · Computer vision. Real-time YOLO detection connected to a mouse controller. Benchmarked on FPS and inference time.. Stack: Python - [MiniPIM](https://github.com/arrozet/MiniPIM): Oct 2024 to Feb 2025 · C#. Product-information system built for a requirements-engineering course. The model covers entities, roles, and catalogue rules.. Stack: .NET, C#, MySQL - [DAJER](https://github.com/arrozet/malacaton): Water management. Oct 2024 · I Malackathon · 2nd, Accessibility. Water-management dashboard with reservoir maps, queryable levels, and a 12-month forecast. Built in one weekend.. Stack: Oracle Autonomous Database, Hugo, JavaScript - [Feed The Leader](https://github.com/arrozet/FeedTheLeader): Mar 2024 to Oct 2024 · C#. Clicker game about feeding a leader. The first project I shipped that people played.. Stack: Unity, C# ## Competitions - [Cursor Build Night Málaga](https://arroz.foo/#record): Cursor. Jul 2026 · 4th place. Four-person team. 105 minutes. Traffic-jam challenge. - [II Malackathon](https://arroz.foo/#record): University of Málaga. Oct 2025 · Best Overall Solution. Agentic platform for mental-health data analysis, built in five hours. - [Mercedes-Benz Data Science Challenge](https://arroz.foo/#record): Mercedes-Benz. Apr 2025 to Jun 2025 · 3rd prize. Vehicle purchase timing model. - [Dedalus Datathon Andalucía](https://arroz.foo/#record): Dedalus. Mar 2025 · 4th place. Clinical summary assistant built for the Dedalus Datathon Andalucía. - [I Malackathon](https://arroz.foo/#record): University of Málaga. Oct 2024. First edition. Reservoir data and a 12-month forecast. ## Education - [BSc, Software Engineering](https://arroz.foo/#education): University of Málaga. Sep 2022 to Jul 2026 · 9.20 / 10 · 1st of 100+. Earned the highest academic distinction in 50% of the degree credits. That amounts to 18 subjects. ## Optional - [GitHub](https://github.com/arrozet): @arrozet - [LinkedIn](https://www.linkedin.com/in/ruben-oliva/): in/ruben-oliva - [Blog](https://blog.arroz.foo/): Writing - [How I work](https://arroz.foo/#method): Decisions need evidence; Prototype and product are different; Choose the stack for the problem; Keep a human responsible; Assign ownership; Use metrics for a reason.