DevOps - Inference squad (AI Tribe) - H / F

Groupe iliad; Paris; Sur place; EUR 60 000 - 80 000; Plein temps

Résumé du poste

Une entreprise innovante recherche un Ingénieur DevOps passionné pour rejoindre son équipe AI. Dans ce rôle, vous serez responsable de la conception et de l'exploitation des pipelines CI/CD pour des applications d'IA, garantissant une performance optimale et une sécurité renforcée. Vous collaborerez avec des équipes interfonctionnelles pour intégrer de nouvelles technologies et améliorer la fiabilité des solutions d'IA. Si vous êtes motivé par l'optimisation des infrastructures et que vous souhaitez contribuer à des projets d'avant-garde dans le domaine de l'intelligence artificielle, cette opportunité est faite pour vous.

Qualifications

• Expertise in Golang and Kubernetes is essential for this role.
• Experience with cloud providers like AWS, Azure, or GCP is required.

Responsabilités

• Develop and operate the backend of AI products, focusing on scalability and security.
• Design CI/CD pipelines tailored for AI applications to ensure efficiency.

Connaissances

Golang

GitOps

Kubernetes

Cloud Computing

Serverless Architectures

AI Model-Serving Technologies

Infrastructure as Code (Terraform)

Network Configuration

System Administration

French Language

Outils

CI/CD Pipelines

Container Orchestration Systems

Description du poste

About the job

At Scaleway, our AI Tribe is at the forefront of deploying cutting-edge AI technologies. Our Inference Squad specializes in delivering LLM-as-a-Service, facilitating both dedicated and mutualized GPU resources across various client applications. As a DevOps Engineer on this dynamic team, you will play a pivotal role in ensuring the seamless development, deployment, operation, and scaling of our AI products. You will collaborate with a team of engineers and developers dedicated to our AI service offerings, focusing on the infrastructure that supports large language models and various other ML models. Your expertise will drive the optimization and enhancement of our AI deployment pipelines and contribute significantly to our mission of providing robust AI solutions.

Responsibilities

• Develop and operate the backend side of our AI products portfolio.
• Design and implement robust CI/CD pipelines tailored for AI applications, focusing on automation, scalability, and security.
• Monitor and optimize the performance of the AI services, ensuring they meet the strict demands of latency and throughput.
• Lead the integration of new technologies and frameworks that support the advancement of our AI capabilities.
• Collaborate across teams to enhance the scalability and reliability of our AI solutions.
• Ensure the security and compliance of the infrastructure according to industry standards.
• Actively participate in the planning and execution of infrastructure strategies, aiming for continuous improvement in all areas of deployment and operations.

Minimum Requirements

• Strong coding skills in Golang.
• Knowledge of GitOps best practices.
• Good experience with Kubernetes and container orchestration systems.
• Solid background in cloud computing and working with major cloud providers (AWS, Azure, GCP).
• Experience in monitoring and ensuring the reliability of serverless architectures.
• Demonstrated ability to maintain high standards of code quality and system security.
• Effective communication skills in English.
• Experience with AI model-serving technologies and frameworks.
• Proficiency in infrastructure as code tools such as Terraform.
• Knowledge of GPU-based computing and optimization.
• Experience contributing to or managing open-source projects.
• Advanced skills in network configuration, system administration, and optimization.
• Very good command of French is advantageous.

Location

This position is based in our offices in Paris or Lille (France).

Recruitment Process

1. Screening call - 30 mins with the recruiter
2. Manager Interview - 45 mins
3. Home Assignment
4. Team Interview
5. HR Interview - 45 mins
6. Offer sent