If you are here, it is because you know that we are looking for a
Forward Deployed AI Engineer
.
indigo.ai is the leading platform in Italy for building next-generation AI Agents that transform the way companies communicate with their customers.
Since ****, we've been helping enterprises in industries such as finance, insurance, utilities, retail, and e-commerce to evolve their Customer Experience through conversational AI.
We don't just "sell software": we enable a shift in how organizations interact with people, automating millions of conversations every year, reducing operational costs, improving conversion rates, and creating more personalized, scalable, and compliant customer journeys.
Backed by a recent €10 million investment from Azimut, we are on a mission to take this technology general.
This is a unique opportunity to join a well-funded, highly ambitious team and play a direct role in shaping the future of enterprise AI.
To make this happen, we are looking for a Forward Deployed AI Engineer to support our Chief AI Officer in designing AI Agents and taking them live, side by side with our clients in Spain.
What are we looking for?
We are looking for a Forward Deployed AI Engineer to take our AI Agents from design to production, working side by side with our enterprise clients.
We are growing our team in Madrid to support new projects in the Iberian market, and the role reports directly to our Chief AI Officer.
It is a cross?functional role for a T?shaped profile, between technology and business: your value lies in deciding how an assistant should work (its architecture, flows and behavior) and in making it work with real users and traffic, while Product and AI tools handle low?level configuration and detailed debugging.
With the right fit,



the role can grow into delivery leadership: defining how we design AI Agents, mentoring new hires and helping build our AI implementation team as we expand in Europe.
Key Responsibilities:
Design the agentic architecture: decide how to frame each problem (for example, a router agent that hands off to specialized agents) and where gates and guardrails are needed, such as user recognition, queue management and handover to a human agent.
You design the structure before building it, for both chat and voice, which follow the same logic.
Keep hallucinations under control: define the boundaries of each agent, deciding when it answers, when it retrieves information and when it must say "I don't know" instead of making up a plausible answer.
Translate business goals into agent behavior: turn objectives such as "reduce waiting times" or "never share internal details with the user" into precise rules, flows and guardrails.
Take care of the user experience: design tone, messages and channel adaptation (voice, chat, messaging) from the end user's point of view, because perceived quality is part of the solution.
Build with AI: use agentic coding tools such as Claude Code to build, read and validate what they produce, framing problems so that the tools execute them well and judging when the output is correct.
Go live and iterate: monitor performance and KPIs, handle edge cases,



check the quality and reliability of answers and keep improving the solution after go?live.
You own the outcome.
Guide clients' decisions: act as the point of reference who helps clients make the right choices and turns them into implementation.
Coordinate the right people: work closely with Product, DevOps, Customer Success and Technical Support to stay aligned, manage dependencies and remove blockers quickly.
Enable clients: provide training, documentation and ongoing support so that clients can manage and optimize their AI Agents on their own.
You will need:
Agentic architecture judgment: you can design an agentic system end to end (framing it, deciding where and how to use tools and context retrieval, designing the flows) and explain why you made those choices.
Reliability control: you know how to recognize and prevent hallucinations by setting boundaries and understanding when an agent should retrieve, answer or admit it doesn't know.
You treat answer quality as a design responsibility.
A functional, product and UX mindset: you design from the end user's point of view and act as a bridge between business and solution, translating a goal into concrete agent behavior.
Hands?on use of AI to build: you use agentic coding tools such as Claude Code every day to move faster, framing problems for the tools to execute and reading and judging the output well enough to work autonomously.
We don't expect you to write production code yourself.
Proven experience designing and running virtual assistants, agents or AI products, or a concrete portfolio of things you built yourself.
Your track record matters more than your degree: in your applicati

📌 Forward Deployed Ai Engineer (España)
🏢 indigo.ai
📍 España