AI Developer
Junior / Apprendista

Descrizione della Posizione Lavorativa

We are searching for an AI Developer who prefers to avoid repeating work through intelligent automation and good system design — not someone who shirks effort, but someone who avoids unnecessary effort. If your approach to AI goes beyond simple API calls and includes designing systems, orchestrating workflows, and ensuring solutions actually work in production, read on.

This position focuses on systems where AI is one component, not the whole job. You will contribute to features and workflows that embed AI inside real products and business processes.

Key responsibilities

• Build AI-powered features and agentic workflows that integrate with existing products.
• Integrate AI into backend logic, data flows and overall system design.
• Develop AI agents and RAG-based systems.
• Build MCP (Model Context Protocol) connectors and servers to connect models with tools and data sources.
• Design prompts and ensure outputs are structured and validated.
• Work on data flows toward frontend applications, including streaming and complex JSON handling.
• Contribute to AI-Driven Development practices across projects so AI tools are part of the daily workflow.

Required technical profile

• Python 3.12+ with serious use of asyncio (not just imported).
• Strict typing and hands-on experience with Pydantic and Pydantic AI / MCP (personal projects count).
• Experience designing integrations between LLMs and tools/data (connectors, servers).
• Familiarity with RAG systems, prompt engineering, and ensuring typed/structured outputs.
• Ability to handle streaming data and complex JSON towards frontend consumers.
• English proficiency.

AI-Driven Development expectations

AI tools are an integral part of the workflow, not a bonus. Tools such as Cursor or Claude Code (or equivalents) are expected to be used daily to speed up prototyping, reduce repetitive work and focus on system design instead of boilerplate. If you prefer writing everything manually, this role will feel unnecessarily difficult.

Who we are looking for

• You don’t need to know everything, but you should be comfortable with asynchronous Python and curious about AI systems.
• Understand differences between ReAct prompting, Tool Calling and Function Calling.
• Junior profiles are welcome if motivated to learn quickly; mid-level candidates should have a good sense of what works and what doesn’t.
• No legacy code and no unnecessary process — focus on building systems that don’t need constant fixing.

Soft skills

• Flexibility and adaptability.
• Willingness to learn continuously and iterate fast.
• Ability to work independently and in a team.
• Comfort with evolving requirements.

Nice to have

• Vercel AI SDK.
• React / TypeScript experience.
• Experience with SSE streaming and handling typed outputs in frontend environments.
• A full-stack mindset or willingness to develop one.

Compensation & benefits

The role is full-remote. You will receive a MacBook Pro and meal vouchers. Contract type and compensation will depend on experience.

How to apply

Send your GitHub or describe a recent AI project (preferably involving Pydantic AI). No slides or long introductions — share code and technical thinking.

Requisiti

Comfortable with asynchronous Python; hands-on experience with Pydantic / Pydantic AI (personal projects accepted); familiarity with RAG and prompt patterns (ReAct, Tool Calling, Function Calling); English proficiency; daily use of AI-assisted development tools.