Giovanni Romero
Backend EngineerAI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Full Stack Developer · AI Automation Engineer · Building with LLMs & n8n
I am a Full Stack Developer with a strong focus on building real products, intelligent automation, and continuous learning. I currently work as a Full Stack Developer at Eciglogística, where I design, develop, and maintain end-to-end web applications, contributing to both frontend and backend with a strong emphasis on clean code, scalability, and best practices. My profile combines modern web development with a growing interest in Artificial Intelligence, particularly Large Language Models (LLMs), workflow automation, and practical AI applications in real-world software. I have built projects in Computer Vision, Deep Learning, and AI-powered content automation systems. I actively share what I learn through my weekly newsletter, where I explain technical topics such as LLMs, fine-tuning, applied AI, and full stack development in a clear and practical way for developers. I am driven by building, learning in public, and continuously improving as a developer. My approach: learn by doing, document the journey, and apply technology to solve real problems. Follow along or reach out at giovanniromero.dev
iLERNA
Higher Technician in Web Application Development , Full Stack Development
September 1, 2023 – June 1, 2025
I.E.S. Tirant lo Blanc
High School Diploma, Social Sciences
January 1, 2018 – January 1, 2020
Nunsys
Professional Certificate in Application Development with Web Technologies (Level 3), Full Stack Development
N/A – Present
Euroformac
Certificate of Professionalism (Level 3), Accounting Management and Administrative Management for Auditing
N/A – Present
Eciglogística
Full Stack Developer
March 1, 2025 – Present
Parque tecnológico de Paterna, Valencia, España · On-site
López & Mora Asesores
Administrativo contable
January 1, 2022 – February 1, 2023
On-site
FreelanceAgent
June 1, 2026 – Present
Full-stack AI web application built with Next.js, TypeScript, FastAPI, PostgreSQL, and LangGraph to help freelancers evaluate job opportunities and generate tailored proposals using LLMs. Key features: - AI-powered job post analysis with profile-aware scoring and risk detection - Proposal generation using OpenAI SDK and LangGraph agent workflows - Intelligent professional profile management with persistent storage - Full-stack architecture: Next.js frontend, FastAPI backend, Prisma ORM, PostgreSQL Demonstrates practical LLM integration, agentic AI design patterns, and production-ready full-stack development with TypeScript and Python. Stack: Next.js, TypeScript, Tailwind CSS, Prisma, PostgreSQL, FastAPI, Python, OpenAI SDK, LangGraph, AI Agents
LCEL LLM Translator – End-to-End AI Translation App with LangChain
January 1, 2026 – January 1, 2026
End-to-end LLM-powered translation application built with LangChain Expression Language (LCEL), FastAPI, and Streamlit, demonstrating production-ready AI pipeline design. The system translates text from English into any target language using a Groq-hosted LLaMA model. Built as a structured LCEL pipeline covering input handling, prompt templating, LLM invocation, and output parsing. Key highlights: - Clean LCEL pipeline architecture — composable, reusable, and easy to extend - FastAPI backend served via LangServe as a production HTTP API - Streamlit frontend for real-time interactive translation - Educational Jupyter notebook explaining the full system step by step - Easily extensible to summarization, content generation, or multi-step reasoning Stack: Python, LangChain, LCEL, LangServe, FastAPI, Streamlit, Groq, LLaMA, Jupyter
Airplane Tracking with YOLOv8
December 1, 2025 – December 1, 2025
This project is a computer vision notebook developed in a Kaggle environment focused on airplane detection and tracking in video. It implements a complete video processing pipeline using YOLOv8, where a video file is analyzed frame by frame to detect airplanes, track their movement over time, and generate an annotated output video with persistent identifiers. The notebook is designed to be easily reusable: by simply updating the video path, the same pipeline can be applied to different videos without modifying the core logic. The project demonstrates the integration of modern object detection models with video processing and multi-object tracking, providing a practical example of real-world computer vision applied to video analysis.
Automated AI-Powered Twitter Content Engine with n8n
December 1, 2025 – December 1, 2025
This project is an end-to-end automation built with n8n that generates and publishes high-quality technical AI content on X (Twitter) without human intervention. Every day at a scheduled time, the workflow selects an unused AI concept from a Google Sheet, generates a long-form technical tweet using an OpenAI language model, publishes it to X, and then marks the concept as used to avoid duplication. The system is designed for consistency, scalability, and content quality, making it ideal for personal brands, technical educators, and AI-focused accounts.
Alpha-Omega Staking DApp — Decentralized Token Staking Platform Built with Solidity & Web3.js
November 1, 2025 – November 1, 2025
Alpha-Omega Staking DApp is a decentralized application that allows users to stake Alpha Tokens (APH) and earn Omega Tokens (OMG) as on-chain rewards. Built entirely on Solidity, Truffle, React.js, and Web3.js, this project demonstrates how blockchain technology can enable transparent, secure, and trustless reward mechanisms. Features Stake & Earn: Lock Alpha tokens (APH) and receive Omega tokens (OMG) as rewards. 100% On-Chain Logic: All balances, rewards, and transactions are handled through smart contracts. Multi-Network Ready: Easily deployable to any EVM-compatible network (Ethereum, Polygon, BNB Chain, etc.). Wallet Integration: Connect directly via MetaMask for seamless interaction. Tech Stack Solidity (v0.8.4) — Smart contract architecture and staking logic Truffle — Compilation, testing, and multi-network deployment React.js — Frontend framework for the DApp interface Web3.js — Blockchain interaction and wallet connection 🌐 Learning This project highlights how decentralized staking mechanisms work behind the scenes and how frontend applications communicate securely with blockchain networks.
Binary Cat–Dog Classifier
November 1, 2025 – November 1, 2025
Binary Cat–Dog Classifier is a deep learning project that demonstrates an efficient approach to binary image classification using modern convolutional neural networks. The model is trained on the Oxford-IIIT Pet Dataset, leveraging transfer learning with a ResNet-34 backbone to accurately distinguish between cat and dog images. This project includes the full pipeline: dataset preparation, exploratory visualization, model training, performance evaluation, and prediction on external images. With only four fine-tuning epochs, the classifier achieves over 99% accuracy, making it a strong example of how transfer learning can produce high-performance models even in small-scale experiments. Additionally, the notebook provides reproducible setup steps, deterministic validation splits, and clean model export, making it suitable as a template for future image recognition tasks.
Certificado profesional de Google Marketing Digital y E-Commerce
Google Career Certificates
June 23, 2026 – Present
Cultural Fit Analysis
The candidate's project portfolio demonstrates a strong inclination towards innovation, particularly in AI and automation, which could be a good cultural fit for a forward-thinking tech environment. The breadth of technologies explored (web3, computer vision, full-stack, AI) suggests adaptability and a continuous learning mindset. However, the professional experience is limited to one full-stack role, and the education is ongoing, which might indicate a need for mentorship in a senior backend role.
Soft Skills & Operational Fit
The candidate's previous accounting role suggests strong attention to detail, data organization, and process management, which are valuable transferable skills for structured software development and operational efficiency. The diverse personal projects indicate a proactive, self-driven learning attitude and problem-solving capabilities.