Job Summary

• Design, develop and deploy GenAI and LLM applications in production across several business domains.
• Build RAG pipelines and multi-agent systems.
• Integrate AI solutions with the client's existing IT tools and platforms.
• Set up AI development practices that cover code quality, security and compliance.
• Turn business needs into AI architecture and a delivery roadmap.
• Support AI adoption from discovery to deployment, and help grow AI literacy across teams.
• Work in agile delivery with client IT and engineering teams.

Key Responsibilities

• Design, develop and deploy GenAI and LLM applications in production across several business domains.
• Build RAG pipelines and multi-agent systems.
• Integrate AI solutions with the client's existing IT tools and platforms.
• Set up AI development practices that cover code quality, security and compliance.
• Turn business needs into AI architecture and a delivery roadmap.
• Support AI adoption from discovery to deployment, and help grow AI literacy across teams.
• Work in agile delivery with client IT and engineering teams.

Skill Requirements

Technical skills (must have)

• Strong hands-on experience deploying production-ready Generative AI solutions.
• LLM-based applications and RAG pipelines.
• Architecting multi-agent systems with current frameworks, such as LangGraph, CrewAI, AutoGen or Semantic Kernel.
• Cloud deployment on Azure, AWS or GCP.
• MLOps and LLMOps: CI/CD, monitoring and model lifecycle.
• Excellent Python programming.

Nice to have

• Fine-tuning foundation models.
• Experience with AI adoption and change management.
• AI use cases in engineering, design or construction.
• Experience guiding or coordinating a small team.

Other Requirements

• Fluent English, written and spoken.
• Based in Europe, with the right to work in the EU and the ability to be onsite a few days per week.
• French is a plus.