AI Engineer

TextYess S.R.L.; United States; On-site; USD 120,000 - 170,000; Full time

Job summary

TextYess, an AI-first CRM, turns conversations into revenue and operates on-site with WhatsApp, email and voice. You’ll join the AI team to build the agentic runtime for proactive agents, handling grounding, retrieval orchestration, scoring and guardrails from day one.

You’ll optimize multilingual quality, reduce latency and cost, profile requests, and ship measurable improvements while owning outcomes and collaborating with international talent to disrupt the market.

Qualifications

• 2+ years shipping software professionally, with at least one LLM feature touched by real users.
• Understanding of RAG, embeddings, vector search and reranking.
• Strong Python and backend fundamentals with attention to latency and cost.

Responsibilities

• Grounding and retrieval fixes to ensure correct product availability in responses.
• Balance exact match and semantic search within a single ranking.
• Ensure multilingual quality across Italian, English, and other languages.
• Profile requests, test prompts and model changes to reduce latency and cost.
• Develop evals and maintain Langfuse traces for production quality.

Skills

2+ years shipping software

LLM features

RAG system

Python / backend

Tools

Langfuse

LangSmith

Braintrust

Arize

Humanloop

Job description

Ciao, we're TextYess

We'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.

We believe the future of commerce is warmer, more human than ever - just at a scale no human team could pull off alone.

We'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.

The role

Join 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.

What you'll actually be doing

• Grounding. 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.

• Exact match vs. semantic. 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.

• Multilingual quality. Our customers write in Italian, English, and more. An agent that answers in the wrong language is worse than one that says nothing.

• Latency and cost. 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.

• Evals that catch problems before customers do. Every conversation has a Langfuse trace, and we have a golden-dataset harness. Making it actually predict production quality is open work.

• Deciding what's worth saying. Ranking, scoring, and suppressing proactive insights so the agent interrupts a customer only when it has earned it.

What you bring

• 2+ years shipping software professionally, including at least one LLM feature real users touched — a chatbot, a RAG system, an agent. Not a weekend project.

• You know how RAG actually behaves: embeddings, vector search, chunking, reranking, and where each one breaks.

• You can read traces. 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.

• Strong Python and backend fundamentals, and the instinct to measure latency, cost and quality instead of guessing.

• Nice to have: search infra (Elastic, Algolia, Qdrant, Weaviate), fine-tuning, graph search, you know how e-commerce operate.

Why TextYess

• Real ownership, from day one. No layers, no waiting your turn: you'll own outcomes, not just tasks.

• Lean team, big impact. You'll work shoulder-to-shoulder with top-notch international talent, ready to disrupt and leave a mark.

• Build, don't maintain. We're early enough that most of what you touch doesn't have a playbook yet, you get to write it.

• Grow as fast as you push. Roles and responsibilities scale with what you prove you can do, not with tenure.

• A team that actually likes each other. We're a dynamic, close-knit crew that moves fast, laughs a lot, and has each other's backs.

Our hiring process

We keep it real and reasonably fast:

1. Screening call, let's just talk. Communication, fit, the basics.

2. Interview + live case study, Let’s deepdive into technicalities of the role.

3. Founder & Team conversations, here you meet the people you'd actually work with.

4. Debrief, reference check, and decision. We move quickly once we're there.

TextYess is an equal opportunity employer. We welcome applicants of all backgrounds and experiences.