Since 2014, Wiremind has positioned itself as a technical company transforming the world of transport and events with a 360° approach combining UX, software, and AI.

Our expertise lies primarily in optimizing and marketing our clients' capacity. We work on various projects such as ticket forecasting and pricing, 3D optimization of air freight or scraping competitor prices. Our applications are the preferred tool of companies such as SNCF, United Airlines, Qatar Airways or even PSG to visualize, analyze and optimize their capacity.

Dynamic and ambitious, we strive to maintain our technical DNA which is the engine of our success. The company, profitable and self-financed since its creation 10 years ago, is mainly composed of engineers and experts and currently supports the growth of our business model based on "software-as-a-service" solutions.

Your missions 🚀

As a Generative AI Intern, you will join Wiremind's emerging GenAI team and work directly under the supervision of our Lead GenAI Engineer. You'll contribute to developing LLM-powered features (most likely in Cayzn) that help airlines and railways make better pricing and operational decisions.

CAYZN is our advanced Revenue Management Solution for the transportation industry, helping our client to optimize their capacity with dynamic pricing. It offers an user-friendly interface coupled with data vizualisation and powerful automation workflows with a business rules engine. Leveraging machine learning models and LLM-based systems, CAYZN is able to recommend and automatically set the best price to fill our client means of transportation (bus, airlines or railways).

The GenAI projects you'll work on:

Our team is building LLM-based systems to analyze services (flights, trains), recommend pricing actions, and help revenue managers define automated strategies using natural language.

What the job looks like in practice:

We approach GenAI with the same rigor as traditional ML: systematic evaluation, iterative improvement, model selection, and structured experimentation. On a day-to-day basis, you can expect to:

• Design and run experiments to test different approaches for the projects above
• Prompt engineering through systematic testing and refinement
• Develop evaluation frameworks including "LLM-as-judge" approaches and metrics aligned with expert preferences
• Benchmark LLM models (GPT-4, Claude, etc.) to find optimal cost/performance tradeoffs for production constraints
• Break down complex problems into simpler, specialized sub-tasks that LLMs can handle more reliably
• Analyze failure modes and edge cases in LLM outputs
• Document and share your findings with the broader engineering and product teams

Your profile 🔍

Hard skills:

• You are currently pursuing a Master's Degree in computer science or data science
• Solid Python programming skills and experience working on structured projects
• Experimented with LLMs (personal projects, coursework, hackathons) and eagerness to learn more
• Good understanding of fundamental machine learning concepts and evaluation metrics

Soft skills:

• Curiosity about applying AI to solve real business problems in production environments
• Strong analytical skills and enjoy iterative experimentation
• Clear communication and ability to explain technical concepts to non-technical stakeholders

Nice-to-have:

• Familiarity with prompt engineering best practices
• Interest in revenue management, pricing, or optimization problems

Technical stack:

• Backend: Python 3.11+ with SQLAlchemy, Remoulade, Flask/FastAPI
• LLM Tools: LiteLLM, Langfuse
• Gitlab for continuous delivery
• Kubernetes for infrastructure

What we offer for 6 months 🤌

By joining us, you will integrate:

• A self-financed startup with a strong technical identity! 🧬
• Beautiful 900 m² offices in the heart of Paris (Bd Poissonnière) ✨
• Attractive remuneration 💪
• A caring and stimulating team that encourages skills development through initiative and autonomy
• A learning environment with opportunities for evolution 🧑‍💻

You will also benefit from:

• 1 day of remote work per week
• A great company culture (monthly afterworks, regular meetings on technology and products, annual off-site seminars, team-building…)

Our recruitment process 🤞

1. A screening interview with Anne-Laure, our Senior Talent Manager
2.  A technical interview with Mehdi our Lead Gen AI
3. A technical test/business case to prepare for
4. A presentation at our offices in the presence of the manager

Wiremind is committed to equality of opportunity, diversity, and fairness. We encourage all candidates with the necessary experience to apply for our job offers.