Agents, automation and RAG in real products that get paid — not toy demos. I document decisions, costs and results in Spanish, for devs who feel AI is moving faster than they are.
I build and maintain the automation; you get the hours back. Published prices, fixed scope, no fine print.
“You answer the same question twenty times a day. You copy data from an email into a spreadsheet. You chase invoices, reminders and reports a machine could handle alone.”
≈ COP 1,000,000
I review your operation, find the 3-5 tasks eating most of your hours, and deliver a prioritized plan with estimated hours saved and tooling costs.
≈ COP 2 – 6 million
I build the automation end to end with n8n, AI agents and your current tools. You get documentation and a short how-to video for your team.
≈ COP 1.2 – 3 million
I maintain, monitor and extend your automations every month. When your tools change, I adjust things before you notice.
I take at most 3 retainers at a time, so I can respond fast and with quality. This is not an agency: you work directly with me.
My own products with real clients, plus senior production experience
Full parking management solution in production: Astro landing page, React Native Android app for attendants, and web admin panel. Features real-time vehicle in/out registration, dashboard with occupancy and revenue reports, monthly plans and renewals, income analytics, and 24/7 support.
Built with
A mobile-first habit tracking application that turns daily routines into an engaging self-improvement journey. Features a 6-tier league system (Beginner to Titan), streak tracking, statistics dashboard, ranking system, Google OAuth, and email authentication. Built with Next.js 14, Prisma, and PostgreSQL.
Built with
High-reliability web application built with a strict TypeScript stack and microservices architecture. NestJS backend, React frontend, PostgreSQL, Docker, and AWS. Focus on zero-downtime deployments, automated testing pipelines, and CI/CD. Improved system stability and deployment frequency.
Built with
Led the engineering team building scalable distributed systems. Designed API architecture and service communication patterns; mentored developers on clean architecture and testing. Stack: NestJS, React, MongoDB, Docker, GCP. Reduced deployment friction and improved team velocity.
Built with
Built a production-ready RAG system for semantic search over documentation. FastAPI backend, AWS Lambda, and PostgreSQL. Focus on cost optimization, prompt engineering, and response quality. Demonstrates AI engineering in a real product context.
Built with
What I'm building and studying right now: production-grade systems, not just POCs.
Building production-grade serverless architectures on AWS and exploring multi-tenant SaaS patterns with Lambda, API Gateway, and RDS Aurora. Studying cost optimization strategies for bootstrapped startups. Target: AWS SA Professional certification (2026).
Stack: Next.js frontend, FastAPI backend, AWS Lambda, PostgreSQL. Implementing semantic search over internal documentation and experimenting with prompt engineering and retrieval optimization.
Integrating OpenAI and Anthropic APIs into existing TypeScript/Node.js services. Building reusable AI feature modules for SaaS applications with focus on context management, token optimization, and error handling at scale.
Learning AWS SageMaker, model deployment patterns, and monitoring. Exploring fine-tuning workflows with Hugging Face and LoRA/PEFT. Target: AWS Machine Learning Specialty certification (2026).
Designing cost-effective AI-native SaaS architectures. Comparing serverless vs. containerized inference workloads and building deployment pipelines for LLM-powered features.
Engineering logs: decisions, code and numbers from what I build.
March 2, 2026 · 4 min read
March 2, 2026 · 2 min read
I've spent 7+ years building software that lives in production: TypeScript, React, Node.js and AWS, for retail, IoT, telecom and SaaS. Today I'm a senior engineer and I get paid to integrate AI into real products: agents with Claude, automation with n8n, RAG over private documents.
Besides my job, I teach applied AI every week at a programming academy and build my own products in public: Parqando (parking management with real clients), a production RAG assistant, and the automations I use daily. That's where everything I publish comes from: the full process, with decisions, costs and numbers — not the perfect tutorial.
I believe you learn more from someone one step ahead showing the process from the field than from a guru watching from the box seats. In Spanish that seat is still mostly empty, and this site exists to fill it: document, don't invent.
Is your company looking for a senior remote engineer (cloud + AI)? I remain open to those conversations. Write me.
Want to automate something, propose a project, or ask about the course?