Valeo is a tech global company, designing breakthrough solutions to reinvent the mobility. We are an automotive supplier partner to automakers and new mobility actors worldwide. Our vision? Invent a greener and more secured mobility, thanks to solutions focusing on intuitive driving and reducing CO2 emissions. We are leader on our businesses, and recognized as one of the largest global innovative companies.

Duration: 11 months
Eligibility: Final year students or recent graduates in Computer Science, AI/ML, Data Science, or equivalent

About the Role:

We are looking for a passionate and self-motivated AI Intern to support our ongoing projects in artificial intelligence, machine learning, and data analytics within the Google Cloud Platform (GCP) ecosystem. The ideal candidate will collaborate with engineering and product teams to design, develop, and test AI-powered solutions using tools like Vertex AI, BigQuery, AutoML, and other GCP-native services.

Our current focus is the development of an advanced chatbot and document generation platform capable of interpreting and generating content in various formats, including text, tables, and flowcharts. The solution is built on Google Cloud Platform (GCP) and integrates with LLM-based workflows. As an AI Intern, you will support the design and implementation of AI services such as retrieval-augmented generation (RAG), structured content generation, and workflow automation.

Key Responsibilities:

• Develop and fine-tune prompt chains for chatbot and content generation workflows using Vertex AI / Gemini APIs

• Assist in implementing Retrieval-Augmented Generation (RAG) pipelines to ground LLM outputs on company data

• Support flowchart and structured table generation using AI (e.g., diagrams.net JSON or Mermaid format)

• Automate data and prompt workflows using N8N or similar no-code/low-code orchestration tools

• Work with structured (tables, JSON) and unstructured (text, PDF) content formats

• Contribute to basic evaluations and improvements of chatbot responses

• Document your work, findings, and results for reproducibility and future scaling

Required Skills:

• Basic programming knowledge in Python

• Understanding of prompt engineering and generative AI concepts

• Exposure to LLMs (like Gemini, Claude, GPT-4) for chatbot and content generation
   

• Practical experience or coursework with TensorFlow or PyTorch

• Ability to work with structured data (e.g., tables in pandas, JSON, CSV)

• Strong curiosity, willingness to learn, and ability to take initiative

Nice to Have (or Will Learn During Internship):

• Experience with RAG (Retrieval-Augmented Generation) using tools like LangChain or LlamaIndex

• Exposure to Agentic AI frameworks (e.g., OpenAI agents, CrewAI, LangGraph) for tool-assisted task handling

• Familiarity with Mermaid.js or diagrams.net JSON format for flowchart generation

• Familiarity with Google Cloud Platform (GCP) services like Vertex AI, BigQuery, Cloud Storage

• Workflow automation experience with N8N, Zapier, or Cloud Workflows

• Basic front-end integration using Streamlit or React (optional)

What You’ll Learn:

• Practical implementation of LLM pipelines in a real-world business environment

• How to design and evaluate prompt flows for accuracy and usability

• Structured document and flowchart generation using generative models

• Real-world exposure to AI/ML projects using cutting-edge GCP tools

• Opportunity to contribute to scalable and production-grade AI systems