Senior AI Engineer

Were 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. Youll 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) 16 React 19 PostgreSQL AWS ECS.

The Team

Were 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. Youd 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. Well 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 isnt 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 Youll Do

You wont be experimenting in a notebook. Youll 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 - Youre one of three engineers building the product. Youll have opinions on architecture push back on ideas that dont make sense and drive features from we should do X to production. The scope grows as fast as you do.

Whats Already Built

Were 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.

Youll work in a TypeScript monorepo: 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 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 (well 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. Youll be in the trenches with us. Some days youll solve problems no one has solved before. Some days youll have to figure things out from scratch with no playbook. Ownership is total - from idea to production its yours. Its not easy but if you want comfort and hand-holding this isnt 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). Its a pretty good one
• Fully remote in Italy. We have an office and you are welcome to join but thats 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 youll 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 youve written about AI/LLMs. Wed love to hear from engineers who are genuinely passionate about building with AI at scale.