About the Role
Always Friday is a 9-person startup (4 founders + 5 team members) building the first AI-powered humanless event agency. With 40+ AI agents in production and real paying customers, we are looking for another Senior AI Engineer to help us accelerate. You will build multi-agent workflows, write system prompts in Italian and English, and ship to production daily. Equity is included.
Companies brief our AI on their event needs – whether it's a corporate retreat for 200, team building in Tuscany, or a product launch in Milan. Our platform then handles the entire process: gathering the brief through conversation, searching venues, processing supplier proposals, and managing the event lifecycle. This is all done through natural language, eliminating forms and back-and-forth emails.
Our Stack
- TypeScript monorepo (Turborepo + Bun)
- Mastra Framework
- Azure OpenAI (GPT-5.2)
- Next.js 16
- React 19
- PostgreSQL
- AWS ECS
The Team
We are a team of 9, including 4 founders and 5 team members. Lorenzo (CTO) and Daniele (CPO) are actively involved in product development. The engineering team consists of Lorenzo and a Founding Engineer. As the third engineer, you will work directly with both co-founders.
How We Work
- Ship Daily: Our CI/CD goes straight to ECS, meaning your code will be in production the same day.
- AI-first: We leverage tools like Claude Code and Cursor to build faster and provide whatever resources you need for experimentation and accelerated development (e.g., Claude Code subscription or your preferred AI tool).
- Pragmatic: We favor simple solutions, DRY code, and iterative development based on real usage, avoiding over-engineering.
- Flexible: While core hours are 9:15-18:15 CET, we prioritize output.
- Fast: We prefer Slack messages over meetings.
What You'll Do
This role is not about wrapping API calls in a chatbot; it involves building and shipping to real customers using our advanced multi-agent system. We already have 40+ specialized agents across 5 major workflows in production, featuring parallel execution, human-in-the-loop conversations, document understanding, and real-time streaming to a React frontend. Each agent has a specific purpose, a structured output schema, and its place in a larger orchestration.
First month – Learn the system, ship real things:
- Understand the codebase, agent coordination, and workflow deployment to production.
- Pair with Lorenzo on existing workflows – fixing bugs, improving prompts, and adding 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, and 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:
As one of three engineers building the product, you will contribute opinions on architecture, challenge ideas that don't make sense, and drive features from concept to production. The scope of your role will grow with your capabilities.
Requirements
Must-have:
- 5+ years of software development experience, with real production AI/LLM experience (not just prototypes).
- Prompt engineering: experience with structured outputs, chain-of-thought, and multilingual prompts.
- TypeScript: advanced proficiency (generics, Zod, type inference).
- Workflow orchestration: experience with multi-step agent pipelines and parallel processing (Mastra, LangGraph, or similar).
- Full-stack: ability to connect 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 interacts with Italian customers.
- English: strong – for documentation, research, and team communication.
- Based in Italy, remote.
Nice-to-have:
- Mastra Framework (training will be provided).
- 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).
This is a startup environment. You will be in the trenches with us, solving novel problems and often figuring things out without a playbook. Ownership is complete, from idea to production. It's challenging, but if you seek comfort and hand-holding, this role is not for you.
Benefits
- €55-65k RAL
- Stock Options: As a seed startup, joining now offers significant potential if we succeed.
- Private Health Insurance: Comprehensive coverage with Generali.
- Fully remote in Italy, with an optional office presence.
- MacBook Pro as your company device.
- Claude Code subscription (or AI tool of your choice).
- Direct product influence: Your contributions will be significant in a team of 10.
- Work on one of the most advanced multi-agent systems in the Italian market and help define its future direction.
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 are keen to hear from engineers genuinely passionate about building with AI at scale.