Ingénieur Devops IA - CDI (H/f)

Job summary

Industrialize, design, and operate secure, highly available on-premises generative AI platforms, including production services for data and AI workloads and large language models. Responsibilities include automating deployments, optimizing GPU use, maintaining platform reliability and observability, managing incidents, and providing technical leadership in an Agile team. The role uses technologies such as Kubernetes, OpenShift, Terraform, Ansible, vLLM, and Prometheus.

Qualifications

• Engineering degree or Master’s degree (Bac+5) in computer science, data science, or cloud computing.
• At least 8 years of experience deploying technical platforms, including at least 2 years with data, AI, or GPU workloads.
• Experience leading technical work in an Agile team, including backlog prioritization and code review.
• Secret Défense clearance, either current or obtainable.
• Advanced experience with Docker, Kubernetes, OpenShift, CI/CD, Jenkins, GitLab CI, Terraform, and Ansible.
• Experience deploying LLMs to production using tools such as vLLM, Triton, KServe, or OpenShift AI.
• Experience with air-gapped environments, private registries, package and container image mirrors, and model-weight management and transfer.
• Experience securing platforms with secrets management, identity and access management, Kubernetes hardening, image scanning, and GitOps.
• Experience with generative AI platforms, model lifecycle tools, and workflow orchestration.
• Experience operating vector databases and monitoring LLM and GPU metrics.

Responsibilities

• Industrialize deployment of secure, highly available on-premises generative AI platforms.
• Automate repeatable CI/CD deployment of models and services.
• Optimize data and AI workloads, including GPU allocation, GPU sharing, and inference autoscaling.
• Contribute to platform architecture, incorporating security, compliance, and governance requirements.
• Ensure platform resilience using high-availability solutions such as Kubernetes, OpenShift, and Docker.
• Develop and integrate secure, compliant managed services for end users.
• Deploy solutions to production with operations teams.
• Maintain AI platforms, ensuring availability, performance, and security.
• Monitor platform and LLM metrics using observability tools.
• Manage incidents and participate in technical on-call duty.
• Provide technical leadership for a product within an Agile team.
• Manage backlog items and prioritize technical work.

Skills

Certifications

Degrees

Work schedule

Security clearance

Relocation