AI & Automation Engineer Intern. Operations

Madrid, Spain | Oct. 31, 2026

Report as Closed

Company: TaxDown

Country: Spain

Type: Onsite

Employment: Part-time

Description:

Help us build the TaxDown tax team's AI operating system: transform manual processes and expert knowledge into intelligent, measurable and scalable flows. Why this problem is interesting

At TaxDown we help people free themselves from bureaucracy. Behind that experience is a team of tax experts that resolves doubts, reviews cases, fills out models and executes procedures. This puts you in front of the problems that are really difficult to automate: unstructured documents, regulations that change, conversations with users, decisions that require context, and processes where precision really matters. You will build internal products that multiply the capacity of our tax experts. You will work directly with tax experts, responsible for Operations, Data, Product and Engineering, with access to real problems and the ability to take your solutions to production. AI is already part of the team. We have systems in production working alongside our tax experts on problems that almost no one has solved well yet. The commitment to AI is one of the company's annual objectives.

What you will do

Applied AI systems

* Agents capable of executing multi-step operational tasks.

* Tax document extraction and classification systems.

* Internal assistants that combine tax knowledge, user context and operational tools.

* Experimentation with RAG, tool calling, structured outputs and multi-agent flows.

* Human in the loop mechanisms for experts to review, correct and improve the system. Systems and data engineering

Systems and data engineering

• Robust integrations through APIs, webhooks, queues and events.

• Data modeling and pipelines that support operational reporting.

• Data management. errors, retries, permissions, logs and observability. What you build has to survive the income campaign.

• Criteria for deciding when to use deterministic rules, traditional automation or AI. Process design

Process design

* Sit down with the tax team, understand how they work today and find where time and context are lost.

* Propose the ""how it should be."

* Measure if what you have built has improved something. If not, reverse it.

What we are looking for

We don't care if you learned in class, in a hackathon or trying to automate something that bored you: we want to see. how you turn an incomplete idea into something that works. Student of Telecommunications, Computer Science, Industrial Engineering, Mathematics, Physics, Data Science or similar. We are looking for engineering profiles for the way of thinking: systems, data flows, bottlenecks, traceability and measurement If you have designed a protocol or debugged a system with many connected parts, this will be familiar to you.

Requirements:

* Possibility of signing an internship agreement. and your situation is different, tell us anyway.

* Know how to program: Python, JavaScript or similar, and SQL. You don't have to be a senior developer, but you do need to write code, understand a REST API, a webhook and JSON without help.

* Structured thinking: take a fuzzy problem and turn it into a diagram and some steps.

* Real interest in AI. applied.

Our culture

Beyond experience, there are traits that the people at TaxDown share: honesty, judgment and a real desire to learn. We are looking for someone who assumes responsibility, works with ambition and. resilience, and enjoy helping and solving problems with impact.

‍

What we offer

* Real ownership and rapid production. What you build is used the next day and frees up people's hours. real.

* Direct exposure to good people: you will work with tax, Operations, Data, Product and Engineering experts, with access to real problems and the ability to take your solutions to production.

* Quick learning: in a few months you will have designed reliable AI systems, integrated tools via API, modeled complex processes and taken a solution from idea to production.

* Clear to undefined path. The internship is the first stage; Incorporation into a template is the expected result if it works for both parties."

The Stack:

Python, JavaScript/TypeScript, SQL, OpenAI and Anthropic APIs, n8n, Airtable, Metabase and AI-assisted development platforms. You will choose the appropriate tool for each problem: from a workflow in n8n to a service in Python, an integration via API or a complete internal application. We do not expect you to know all this. We do expect you to be able to learn it and build with it quickly.

It is valued:

* Own projects, TFG, hackathons or side projects. RAG.

* n8n, Make, Airtable, Replit, Softr, Notion.

Apply here:

Web: Apply here

Emails: