Description
FriendliAI is hiring a Solution Architect to help enterprises deploy, scale, and operate generative and agentic AI workloads on its infrastructure. The role is hands-on and customer-embedded, involving large-scale LLM and multimodal inference architectures, Kubernetes and containerized workloads, production troubleshooting, CI/CD integration, infrastructure automation, and customer technical workshops. Candidates should have at least three years of experience in cloud infrastructure, DevOps, or reliability engineering, along with expertise in Kubernetes, Docker, Terraform, Helm, distributed systems, GPU computing, and AI model serving.
