📍 Paris, Station F · On site · Internship · 4–6 months · Spring 2027

Build agents that do mechanical engineering

Faber builds AI agents that carry out mechanical engineering work: creating CAD models, producing technical drawings, inspecting parts, and preparing manufacturing.

Our users work with physical parts. A model that looks convincing can still have the wrong dimensions. A successful tool call can still produce an unusable result. Making these agents useful means giving them the right tools, the right feedback, and a way to check their work.

We’re looking for an AI engineering intern to build agents and deliver complete projects for our industrial customers.

You’ll take a customer problem from understanding their workflow to building, evaluating, and delivering a solution they can use. The founders and engineering team will work with you on scope, technical decisions, and delivery, while giving you room to take ownership and drive the project forward.

What you’ll work on

• Own a customer project end to end, from the first conversation and experiments to a working product and feedback from users.
• Build the agent loop, tools, and interface needed to solve the problem, with technical support from the team.
• Design and run evaluations to understand what works, investigate failures, and improve the reliability of your solution.
• Make your product work on real jobs, including concurrent execution, understandable failures, and cost tracking.
• Build development tools to inspect runs, compare approaches, debug failures, and iterate faster.

You’ll work closely with the technical team, with regular technical discussions and code reviews. Your project will have a clear scope, real users, and a result to deliver.

You might be a good fit if

• You’re a master’s or final-year engineering student with strong software engineering fundamentals, comfortable building and debugging in Python.
• You have built something with language models and tools, and can explain where it worked and where it broke. Personal projects, coursework, and open-source contributions all count.
• You want end-to-end ownership: you enjoy taking a problem from an initial idea to something people can use, and follow through on what you build.
• You show high agency and a bias for action: you seek out missing information, try approaches, and ask for help when it moves the project forward.
• You care about product quality and can make pragmatic decisions with the team about what matters most to the customer.
• You actively use AI coding tools and develop your own ways to experiment, inspect, and ship software.