Artificial Intelligence Engineer
Pubblicato il 19-10-2026 - TextYess in Italia
ppWe'rethe AI-first CRM that turns conversations into revenue. On-site, WhatsApp, email, voice: our AI Agents sell, support, and retain customers for the best B2C brands out there, autonomously. /p pWe believe the future of commerce is warmer, more human than ever - just at a scale no human team could pull off alone. /p pWe've raised €3M+ and work with brands like Ducati, Pittarosso, MC2 Saint Barth, and Doppelgänger. We're a lean, fast, Italian-born scale-up now expanding our story internationally and this role is a big part of writing it. /p h3The role /h3 pJoin our AI team to build the agentic runtime for proactive agents: context building, tool/retrieval orchestration, scoring, and guardrails. You’ll own production components from day one and work directly on the “signal vs. noise” call. /p h3What you'll actually be doing /h3 ul libGrounding. /b The agent sometimes says a product is unavailable when it's in stock. Fixing that is a retrieval problem, a prompt problem, and an eval problem at the same time. /li libExact match vs. semantic. /b Semantic search is good at "warm jacket for winter" and bad at a SKU, a size, or a specific variant. We need both, in one ranking. /li libMultilingual quality. /b Our customers write in Italian, English, and more. An agent that answers in the wrong language is worse than one that says nothing. /li libLatency and cost. /b A customer is waiting on their phone. You'll profile requests, test prompt and model changes, and ship improvements you can point at on a graph. /li libEvals that catch problems before customers do. /b Every conversation has a Langfuse trace, and we have a golden-dataset harness. Making it actually predict production quality is open work. /li libDeciding what's worth saying. /b Ranking, scoring, and suppressing proactive insights so the agent interrupts a customer only when it has earned it.
/li /ul h3What you bring /h3 ul lib2+ years shipping software professionally /b, including at least one LLM feature real users touched — a chatbot, a RAG system, an agent. Not a weekend project. /li libYou know how RAG actually behaves /b: embeddings, vector search, chunking, reranking, and where each one breaks. /li libYou can read traces. /b Given a bad answer in production, you can find why: retrieval missed, the prompt was wrong, the model picked the wrong tool. Langfuse, LangSmith, Braintrust, Arize, Humanloop — any of them. /li libStrong Python and backend fundamentals /b, and the instinct to measure latency, cost and quality instead of guessing. /li libNice to have: /b search infra (Elastic, Algolia, Qdrant, Weaviate), fine-tuning, graph search, you know how e-commerce operate. /li /ul h3Why TextYess /h3 ul libReal ownership, from day one. /b No layers, no waiting your turn: you'll own outcomes, not just tasks. /li libLean team, big impact. /b You'll work shoulder-to-shoulder with top-notch international talent, ready to disrupt and leave a mark. /li libBuild, don't maintain. /b We're early enough that most of what you touch doesn't have a playbook yet, you get to write it. /li libGrow as fast as you push. /b Roles and responsibilities scale with what you prove you can do, not with tenure. /li libA team that actually likes each other. /b We're a dynamic, close-knit crew that moves fast, laughs a lot, and has each other's backs. /li /ul h3Our hiring process /h3 pWe keep it real and reasonably fast: /p ul libScreening call /b, let's just talk. Communication, fit, the basics. /li libInterview + live case study /b, Let’s deepdive into technicalities of the role. /li libFounder Team conversations /b, here you meet the people you'd actually work with. /li libDebrief, reference check, and decision /b. We move quickly once we're there. /li /ul pTextYess is an equal opportunity employer. We welcome applicants of all backgrounds and experiences. /p /p #J-18808-Ljbffr