Conduct structured process interviews with leads across Finance, Legal, HR, Operations, and Business / Revenue to map recurring, high-cognitive-load tasks
Identify which tasks are suitable for Claude skill encoding — well-defined inputs, predictable structure, clear success criteria
Write, test, and iterate Claude skills: system prompts, instructions, behavioral rules, few-shot examples, output formats, and edge case handling
Validate each skill directly with end users until it performs reliably for non-technical team members
Maintain a documented skill library with scope, usage guide, known limitations, and update log for each skill
Build and share a reusable methodology for skill writing that other teams can apply independently after the internship

Final-year student (M2 or gap year) from a Tier 1 business or engineering school
Strong working knowledge of Claude and prompt engineering — you understand how LLMs reason, where they fail, and how instruction design affects output quality
Ability to write precise, structured specifications: unambiguous instructions, well-chosen examples, explicit edge case handling
Analytical approach to process decomposition — able to turn a vague workflow description into a defined task with clear inputs and outputs
Fluent English — skills will be written and tested
French is a plus
Comfortable operating with autonomy; the role requires self-direction across five departments simultaneously
Prior experience building Claude skills, custom GPT instructions, or equivalent structured prompt systems that were actually used by others
Exposure to one or more of the target functions: Finance, Legal, HR, Operations, or B2B Sales — enough to recognize where the real friction is
Genuine interest in quantum computing and the deep-tech space

1 day off per month
Half of transportation cost coverage (as per French law)
Meal vouchers with Swile, as well as access to a fully equipped and regularly stocked kitchen

AI Transformation Intern

Key skills