Senior AI Engineer

We're a 9-person startup (4 founders + 5 team members) building the first AI-powered humanless event agency. We have 40+ AI agents in production, real paying customers, and we need another senior engineer to help us move faster. You'll build multi-agent workflows, write system prompts in Italian and English, and ship to production daily. Equity included.

Companies tell our AI what they need - a corporate retreat for 200, a team building in Tuscany, a product launch in Milan - and our platform handles the rest: gathering the brief through conversation, searching venues, processing supplier proposals, and managing the entire event lifecycle.

No forms. No back-and-forth emails. Just natural language.

Our stack

TypeScript monorepo (Turborepo + Bun), Mastra Framework, Azure OpenAI (GPT-5.2), Next.js 16, React 19, PostgreSQL, AWS ECS.

The Team

We're 9 people total - 4 founders and 5 team members. Two co-founders work on the product daily: Lorenzo (CTO) and Daniele (CPO) . The engineering team is Lorenzo and a Founding Engineer. You'd be the third engineer, working directly with both co-founders.

How We Work

• Ship daily - CI/CD goes straight to ECS. Your code hits production the same day.
• AI-first - We build with Claude Code, Cursor, whatever makes us faster. We'll give anything you need to experiment and build faster (eg. Claude Code subscription or the AI tool you prefer)
• Pragmatic - Simple solutions, DRY code, iterate based on real usage. No over-engineering.
• Flexible - Core hours 9:15-18:15 CET. We care about output.
• Fast - Slack message > meeting. Always.

Tasks

Why This Role

Most "AI Engineer" roles are about wrapping an API call in a chatbot. This isn't that.

We have 40+ specialized agents across 5 major workflows already in production - parallel execution, human-in-the-loop conversations, document understanding, real-time streaming to a React frontend. Every agent has a purpose, a structured output schema, and a place in a larger orchestration.

What You'll Do

You won't be experimenting in a notebook. You'll be building and shipping to real customers.

First month - Learn the system, ship real things:

• Understand the codebase, how agents coordinate, and how workflows reach production
• Pair with Lorenzo on existing workflows - fix bugs, improve prompts, add steps
• Ship your first agent or workflow improvement to production

Months 2-3 - Build independently:

• Design and build new agents with bilingual system prompts and Zod output schemas
• Wire AI workflows end-to-end: Mastra steps, API routes, React frontend with real-time streaming
• Own prompt performance on your workflows: measure, optimize, iterate

Months 3-6 - Own entire workflows:

• Architect multi-step pipelines from scratch (parallel execution, concurrency control, error recovery)
• Implement document processing capabilities (PDF, DOCX) with confidence scoring
• Create tools for agents to interact with databases, S3, and external services
• Start shaping what we build next, not just how

After that - You're one of three engineers building the product. You'll have opinions on architecture, push back on ideas that don't make sense, and drive features from "we should do X" to production. The scope grows as fast as you do.

What's Already Built

We're not pre-product. We have a mature codebase with 40+ agents across 5 major workflows : conversational venue search, AI-driven event brief gathering, supplier proposal extraction, and email automation. Real customers use it today.

You’ll work in a TypeScript monorepo: Next.js web app, Mastra + Hono AI service, shared database and streaming packages, human-in-the-loop patterns with suspend/resume.

Requirements

Must-have:

• 5+ years building software, with real production AI/LLM experience (not just prototypes)
• Prompt engineering - structured outputs, chain-of-thought, multilingual prompts
• TypeScript - advanced (generics, Zod, type inference)
• Workflow orchestration - multi-step agent pipelines, parallel processing (Mastra, LangGraph, or similar)
• Full-stack - you can wire AI to a Next.js API route and stream results to a React hook
• PostgreSQL + ORM (Prisma or similar)

Non-negotiable:

• Italian : native/fluent - our AI talks to Italian customers
• English : strong - docs, research, team communication
• Based in Italy , remote

Nice-to-have:

• Mastra Framework (we'll train you)
• Azure OpenAI / GPT-5.2
• LangChain, LangGraph, Vercel AI SDK, CrewAI
• Document processing (PDF, text extraction)
• Hono, AWS (ECS, S3, Lambda), Docker, Terraform
• Observability (Sentry, OpenTelemetry)
• Monorepo tooling (Turborepo, Bun)

A heads up : this is a startup. You'll be in the trenches with us. Some days you'll solve problems no one has solved before. Some days you'll have to figure things out from scratch with no playbook. Ownership is total - from idea to production, it's yours. It's not easy, but if you want comfort and hand-holding, this isn't the place.

Benefits

• €55-65k RAL
• Stock Options : we are a seed startup and joining now means you could make a huge amount of money if we make it
• Private Health Insurance (Generali). It's a pretty good one
• Fully remote in Italy. We have an office and you are welcome to join but that's up to you (no pressure at all)
• MacBook Pro as your company device
• Claude Code subscription (or AI tool of your choice)
• Direct product influence. In a team of 10, everything you build matters
• One of the most advanced multi-agent systems in the Italian market - and you'll help define where it goes

Tell us what excites you about multi-agent AI systems, and share links to your GitHub, AI projects, or anything you've written about AI/LLMs. We’d love to hear from engineers who are genuinely passionate about building with AI at scale.

#J-18808-Ljbffr