4 months ago
Paris, FranceSenior
Responsibilities
- Build and operate infrastructure for serving LLMs and generative models at scale.
- Design, deploy, and maintain Kubernetes-based services optimized for AI inference.
- Develop robust and efficient backend services in Golang.
- Optimize AI serving stacks using vLLM, Triton, and CUDA.
- Integrate AI tooling such as Hugging Face, KServe, and custom components.
- Participate in architecture discussions and make high-impact technical decisions.
- Troubleshoot infrastructure and deployment issues and collaborate on integrating new AI features.
- Contribute to code reviews and knowledge sharing.
Requirements
- Strong production experience with Golang.
- Proficiency with Kubernetes and container orchestration tools.
- Knowledge of LLMs and diffusion models.
- Solid understanding of backend architectures and DevOps practices.
- Hands-on experience deploying and scaling ML models is appreciated.
- Ability to learn emerging AI tools, take ownership, work autonomously, and communicate complex systems clearly.
Benefits
- Hybrid work with up to 3 days remote per week.
- Modern offices with ergonomic workspaces, terraces, and bike facilities.
- Chef-prepared meals at headquarters and a Swile card for regional sites.
- Support for gym memberships, childcare, and caregiver services.
- International and diverse teams where English and French are commonly used.
- Internal mobility and opportunities across the Iliad Group.
Tech Stack
Categories
About Scaleway
Scaleway provides European public cloud infrastructure and AI platforms—compute, storage, networking, bare metal, Kubernetes, and serverless—for developers and businesses. Founded in 1999 and headquartered in Paris, it is a subsidiary of the iliad Group, operating across several European countries with data centers powered by renewable energy since 2017. Customers include France Télévisions, Hachette Livre, and the City of Copenhagen.
