Senior AI Infrastructure Architect

Looking for a Senior AI Infrastructure Architect, English B1+

Project: Designing and building cloud-native, GPU-enabled AI infrastructure and large-scale MLOps platforms to support high-performance AI/ML model deployment and container orchestration.

• Design GPU-enabled Kubernetes clusters for scalable AI workloads.
• Architect and optimize MLOps pipelines and container orchestration systems.
• Configure and manage high-performance cloud environments (GCP/GKE) and AI/ML platform services.
• Integrate NVIDIA hardware acceleration tools to optimize model inference and training.

Requirements:

• Deep expertise in Kubernetes orchestration, containerization, and cloud-native infrastructure design.
• Strong hands-on experience in Google Cloud Platform (GCP), specifically Google Kubernetes Engine (GKE) and Vertex AI.
• Solid proficiency in MLOps platform development and large-scale AI/ML deployment methodologies.
• Deep understanding of the NVIDIA AI ecosystem, including CUDA, TensorRT, Triton Inference Server, and NVIDIA NIM.

Full-time. 6-8 months, start in 2-3 weeks. Hourly rate is negotiable.

——— Контакт: @v_kozyura