Most people offering "AI automation" picked up n8n a few months ago. I spent six years as a software engineer at Amazon and AWS before I built my first workflow, shipping systems that carried real production traffic and had a pager attached to them. I still build the automation in n8n. I just also know what happens underneath it when something goes wrong. What I actually build: 🛠️ All your tools connected in your workflows, the agents don't guess, they use what they need 🤖 Multi-agent workflows in n8n, with RAG over your own documents so answers come from your data, not a guess 📥 Document automation: inbound email triggers, classification, extraction, summarization, built for a law firm managing cases across multiple jurisdictions 🎭 Prompting that adapts to the person using it instead of one rigid script for everyone 🧱 The infrastructure underneath the automation: queues that preserve order under load, isolated processing for sensitive data, systems that scale without someone babysitting them Why it holds up in production: 🏗️ Six years at Amazon and AWS: Lambda, DynamoDB, Cloud Run, CI/CD, canary deployments, I can build infrastructure in AWS or GCP 🔒 Experience handling legally sensitive documents under strict data-processing boundaries 📈 Built a RAG assistant for regional energy community administrators that expanded from one region to three provinces without rewriting the core system ⚡ Nobody asked me to build my most-used AWS project. I noticed a gap, built it anyway, and it became one of the most-used parts of a platform 3,000 Solution Architects relied on daily Based in Brussels, comfortable working into US hours. If you want automation that still works in six months, let's talk.

Pedro Muñoz

Most people offering "AI automation" picked up n8n a few months ago. I spent six years as a software engineer at Amazon and AWS before I built my first workflow, shipping systems that carried real production traffic and had a pager attached to them. I still build the automation in n8n. I just also know what happens underneath it when something goes wrong. What I actually build: 🛠️ All your tools connected in your workflows, the agents don't guess, they use what they need 🤖 Multi-agent workflows in n8n, with RAG over your own documents so answers come from your data, not a guess 📥 Document automation: inbound email triggers, classification, extraction, summarization, built for a law firm managing cases across multiple jurisdictions 🎭 Prompting that adapts to the person using it instead of one rigid script for everyone 🧱 The infrastructure underneath the automation: queues that preserve order under load, isolated processing for sensitive data, systems that scale without someone babysitting them Why it holds up in production: 🏗️ Six years at Amazon and AWS: Lambda, DynamoDB, Cloud Run, CI/CD, canary deployments, I can build infrastructure in AWS or GCP 🔒 Experience handling legally sensitive documents under strict data-processing boundaries 📈 Built a RAG assistant for regional energy community administrators that expanded from one region to three provinces without rewriting the core system ⚡ Nobody asked me to build my most-used AWS project. I noticed a gap, built it anyway, and it became one of the most-used parts of a platform 3,000 Solution Architects relied on daily Based in Brussels, comfortable working into US hours. If you want automation that still works in six months, let's talk.

Available to hire

Most people offering “AI automation” picked up n8n a few months ago. I spent six years as a software engineer at Amazon and AWS before I built my first workflow, shipping systems that carried real production traffic and had a pager attached to them. I still build the automation in n8n. I just also know what happens underneath it when something goes wrong.

What I actually build:

🛠️ All your tools connected in your workflows, the agents don’t guess, they use what they need
🤖 Multi-agent workflows in n8n, with RAG over your own documents so answers come from your data, not a guess
📥 Document automation: inbound email triggers, classification, extraction, summarization, built for a law firm managing cases across multiple jurisdictions
🎭 Prompting that adapts to the person using it instead of one rigid script for everyone
🧱 The infrastructure underneath the automation: queues that preserve order under load, isolated processing for sensitive data, systems that scale without someone babysitting them

Why it holds up in production:

🏗️ Six years at Amazon and AWS: Lambda, DynamoDB, Cloud Run, CI/CD, canary deployments, I can build infrastructure in AWS or GCP
🔒 Experience handling legally sensitive documents under strict data-processing boundaries
📈 Built a RAG assistant for regional energy community administrators that expanded from one region to three provinces without rewriting the core system
⚡ Nobody asked me to build my most-used AWS project. I noticed a gap, built it anyway, and it became one of the most-used parts of a platform 3,000 Solution Architects relied on daily

Based in Brussels, comfortable working into US hours. If you want automation that still works in six months, let’s talk.

See more

Language

Spanish; Castilian
Fluent
English
Fluent

Work Experience

Freelance Senior Software Engineer - AI Engineer at Self-Employee
September 1, 2025 - Present
Senior Software Engineer at Amazon
February 1, 2025 - August 31, 2025
Software Engineer - Senior Software Engineer at AWS
October 1, 2021 - January 31, 2025
Software Engineer at Amazon
September 1, 2018 - September 30, 2021

Education

Bachelor's Degree - Software Engineering / Computer Science at Universidad Politécnica de Madrid
September 1, 2013 - July 1, 2017
Master's Degree - Machine learning and Data Science at Universidad de Alcalá de Henares
January 1, 2018 - January 1, 2019

Qualifications

Add your qualifications or awards here.

Industry Experience

Software & Internet
    Automated Case Document Pipeline for a Multi-Jurisdiction Law Firm

    A law firm handling cases across national and international jurisdictions was drowning in manual admin. Someone had to read every incoming email, work out which case it belonged to, and file the attachments by hand before anyone could act on them. I built the system that does that automatically, end to end, with the level of care legal documents actually require.

    How it works:

    📧 Inbound email is triggered and automatically classified by case, no manual sorting
    📎 Attachments are matched to the correct case file automatically, even across parallel active cases
    🧾 Documents are extracted and summarized so the team gets the gist without opening every file
    🔐 Highly sensitive material is processed under restricted boundaries: strict limits on what reaches third-party services, agreed with the firm before a single document moved

    Built to actually hold up:

    🧠 n8n orchestrates the entire pipeline, from the moment an email lands to the moment a summarized case file is ready
    🧩 Custom logic beyond what n8n’s built-in nodes cover (classification rules, case-matching) written in TypeScript
    🗂️ Supabase (PostgreSQL) for structured case data
    ☁️ Cloud Run functions, written in Python, handle extraction from encrypted files, format conversion, and information extraction
    🔁 A FIFO queue guarantees per-client message ordering, so a burst of emails from one client doesn’t get processed out of sequence
    📈 The same queue absorbs peak load without over-provisioning infrastructure the rest of the time

    Orchestrated end to end in n8n. Built in close coordination with the firm to get the confidentiality boundaries right before the automation touched a real case.

Hire a Full Stack Developer

We have the best full stack developer experts on Twine. Hire a full stack developer in Brussels today.