pIf you are here, it is because you know that we are looking for a AI Engineer for our Product team. /ppindigo.ai is the leading platform in Italy for building next-generation AI Agents that transform the way companies communicate with their customers. Since 2016, 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. /ppBacked by a recent €10 million investment from Azimut, we are on a mission to take this technology global. 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. /ppTo make this happen, we are looking for a Product AI Engineer to and work alongside the person who leads AI on the product today. /ph3What are we looking for? /h3pWe are looking for an AI Product Engineer to join our Product team. This role combines software engineering fundamentals, product sense, and hands‑on AI execution. You will own AI features end-to-end—building agentic workflows, designing RAG architectures, establishing evaluation pipelines, and integrating probabilistic AI systems cleanly into our platform. /ph3Key

Responsibilities:
/h3ulliEnd-to-End Feature Delivery: Design, prototype, and ship AI capabilities directly into the product, owning features from initial concept to production deployment. /liliAgentic Pipelines Workflows: Build multi-step agentic workflows, tool-calling frameworks, and decision‑making logic that reliably orchestrate complex enterprise tasks.



/liliRAG Knowledge Architectures: Design and optimize Retrieval-Augmented Generation (RAG) architectures over messy enterprise documents, tuning search strategy, context retrieval, and response grounding. /liliAI Evaluation Quality: Build evaluation frameworks, regression testing suites, and quality gates to measure output accuracy, hallucination rates, latency, and reliability. /liliProduct UX Integration: Align AI features with real user workflows, managing streaming responses, loading states, and edge cases gracefully. /liliObservability Iteration: Monitor production AI features, using telemetry and conversation signals to iteratively refine system performance and safety. /li /ulh3You will need: /h3ulliAgentic Architectures RAG Expertise: Practical experience building agentic systems (tool/function calling, multi‑agent orchestration, state management) and deep familiarity with modern RAG approaches (vector search, hybrid retrieval, chunking strategies, re‑ranking). /liliProduction Experience with LLMs: Hands‑on experience deploying LLM systems with real users or production traffic, with a clear understanding of what breaks in production and how to fix it. /liliElixir AI‑Assisted Workflows: Solid backend engineering fundamentals and hands‑on experience using agentic coding tools (Claude Code, Cursor, Codex) in your daily practice. You will rely on AI assistants to confidently read, write,



and contribute directly to our product codebase, which is built mainly in Elixir. /liliEvaluation Reliability Discipline: Proven ability to test probabilistic systems using objective evaluation suites, quality gates, and guardrails rather than manual output checking. /liliProduct Sense: Ability to solve problems with a scalable product mindset, ensuring solutions work for one client and scale seamlessly for the next ten. /liliLanguage

Skills:
Fluent Italian and good working proficiency in English (B2+). /li /ulh3We will really like (but they are not required): /h3ulliConversational AI Background: Experience with enterprise chatbots, voicebots, CCaaS integrations, or messy real‑world document processing. /liliModel Serving Fine‑Tuning: Hands‑on work with self‑hosting, quantization, or fine‑tuning open‑source models for enterprise data residency and cost efficiency. /liliObservability Cost Attribution: Experience with LLM tracing, latency budgets, and per‑request cost monitoring. /li /ulh3Our values: /h3pAt indigo.ai we prize bVision /b (curiosity and courage to challenge the status quo), bConnection /b (empathy, candor, and trust), bResponsibility /b (ownership, reliability, and follow‑through), and bExcellence /b (the habit of raising the bar and refining until it’s right). If you naturally think ahead, build strong relationships, take accountability, and obsess over the quality of what you deliver, we’re probably a great match. /ph3What do

we offer
? /h3ulliA key role in one of Europe’s fastest‑growing AI scale‑ups, backed by a €10M investment from Azimut. /liliA competitive salary in the range of 38‑45k RAL, commensurate with experience + a performance‑based Premio. /liliA flexible, remote‑friendly work envi

📌 AI Engineer, Product (Milano)
🏢 indigo.ai
📍 Milano