AIOps Engineer

DCG is a recruitment company dedicated to supporting experienced professionals in their career growth. We are currently seeking an AIOps Engineer to join our team and contribute to the development and maintenance of scalable AI infrastructure.

Key responsibilities

• Design, deploy, and maintain vLLM inference services on OpenShift and Kubernetes using bare-metal GPU infrastructure.
• Manage NVIDIA GPU resources, including partitioning and allocation, to ensure optimal utilization across multiple models.
• Automate the model lifecycle, including onboarding, versioning, deployment, and hot-swapping from private registries.
• Build comprehensive observability solutions using Prometheus, Grafana, and OpenTelemetry to monitor infrastructure health and inference performance.
• Implement API Gateway solutions for authentication, rate limiting, and secure routing to inference services.

Requirements

• Over 5 years of experience in DevOps, SRE, or Platform Engineering, with at least 2 years focused on MLOps or LLM platforms.
• Strong expertise in Kubernetes and OpenShift administration within production environments.
• Deep knowledge of NVIDIA GPU technologies, CUDA drivers, and inference optimization techniques like Paged Attention.
• Proficiency in Python for automation and operational tooling, alongside strong Linux administration skills.
• Excellent analytical and problem-solving abilities in complex, distributed systems.

What we offer

• Private medical care package.
• Co-financing for sports activities.
• Access to training and professional development opportunities.
• Dedicated consultant support and an employee referral program.