Descrizione della Posizione Lavorativa
We are looking for an AI Developer who prefers eliminating unnecessary repetition rather than avoiding work. If you see AI as more than just calling an API—if you enjoy designing systems, orchestrating workflows, and making solutions that actually work—this role may suit you.
Role
You will join projects where AI is one important component of a larger system. The job includes building features powered by AI, integrating models into real products and business processes, and working on backend logic, data flows and system design. You will also help spread AI-Driven Development practices across projects.
Key responsibilities
- Build AI-powered features and agentic workflows.
- Integrate AI into real products and business processes.
- Work on backend logic, data flows, and overall system design.
- Contribute to and apply AI-Driven Development practices.
AI-Driven Development (required)
AI tools are part of the daily workflow, not optional. Tools such as Cursor or Claude Code (or similar) should be used regularly to speed prototyping, reduce repetitive tasks and let the team focus on system design rather than boilerplate. If you prefer writing everything manually, this role may feel unnecessarily hard.
Tech stack & what you'll do
The core stack includes Python 3.12+, real use of asyncio (not just imported), strict typing, and Pydantic & Pydantic AI / MCP (Model Context Protocol) to connect LLMs with tools and data. Typical tasks:
- Develop AI agents and RAG-based systems.
- Build MCP connectors and servers to integrate models with tools and data.
- Design prompts and ensure outputs are structured and validated.
- Work on data flows (including streaming and complex JSON) toward frontend applications.
What we're looking for
You don't need to know everything, but you should:
- Be comfortable with asynchronous Python.
- Have hands-on experience (personal projects count) with Pydantic / Pydantic AI.
- Be genuinely curious about AI systems.
- Understand the difference between ReAct prompting, Tool Calling, and Function Calling.
- Have sufficient English proficiency for technical communication.
No legacy code. No unnecessary process. No pretending things are more complex than they are. Focus on building systems that don't need constant fixing.
Junior profiles are welcome if motivated to learn quickly. Mid-level candidates should already know what tends to work and what usually doesn't.
Soft skills
- Flexibility and adaptability
- Willingness to learn continuously
- Ability to work independently and in a team
- Comfort with evolving requirements and fast iterations
Nice to have
- Experience with Vercel AI SDK
- React / TypeScript
- Experience with SSE streaming
- Experience handling typed outputs in frontend environments
- A full-stack mindset or willingness to develop one
How to apply: send your GitHub or describe a recent AI project (preferably involving Pydantic AI). No slides, no long introductions—just code and technical thinking.
Benefits
- Full-Remote working arrangement.
- MacBook Pro provided.
- Meal vouchers.
- Contract type and compensation will depend on experience.
- Location reference: Livorno, LI (Italy).
Requisiti
Comfortable with asynchronous Python; hands-on experience with Pydantic / Pydantic AI; curiosity about AI systems; understanding of ReAct prompting, Tool Calling and Function Calling; English proficiency.
Competenze richieste
Competenze professionali
Asynchronous Python (asyncio)
Python 3.12+
Strict typing
Pydantic / Pydantic AI (MCP)
LLM integration and connector development
RAG systems
Prompt design and output validation
Data flows and streaming (complex JSON)
Competenze trasversali
Flexibility and adaptability
Willingness to learn continuously
Ability to work independently and in a team
Comfort with evolving requirements and fast iterations