AIOps Engineer @ DCG v Česko

Odpovědnosti

1. Design, deploy, and maintain vLLM inference services on OpenShift/Kubernetes running on bare-metal GPU infrastructure
2. Manage NVIDIA GPU resources, including GPU partitioning and allocation, to maximize utilization across multiple models and tenants
3. Automate model lifecycle management, including model onboarding, versioning, deployment, hot-swapping, and rollback from private registries such as Hugging Face Enterprise and S3
4. Implement and manage Horizontal Pod Autoscaling (HPA) based on workload demand, queue depth, and GPU resource https://jobeax.com/link/qk9UrM7q9yRd2OpM vLLM configurations and serving parameters to maximize performance, throughput, and resource efficiency
5. Build and maintain observability and monitoring solutions for AI inference services, including metrics collection, logging, and tracing
6. Instrument vLLM endpoints to expose metrics related to token consumption, latency, throughput, and error rates

O pozici / o projektu

As a recruitment company, DCG understands that every business is powered by experienced professionals. Our management style and partnership approach enable us to meet your needs and provide continuous support. Due to our ongoing growth and the large number of recruitment projects we undertake for our partners, we are currently looking for:

AIOps Engineer

Offer:

• Private medical care
• Co-financing for the sports card
• Training & learning opportunities
• Constant support of dedicated consultant
• Employee referral program

Detail pracovní nabídky

• Ihned
• Práce plně na dálku

Výhody

• Sport Subscription
• Soukromá zdravotní péče
• Employee referral bonus