LLMOps Engineer: Scalable AI Inference on Kubernetes

A next-generation AI startup is seeking an experienced LLMOps Engineer in Toronto to design and optimize LLM infrastructure. You will drive infrastructure automation, architect distributed AI pipelines, and implement production-ready solutions. The ideal candidate has over 5 years in DevOps or AI infrastructure, focusing on LLMOps, and possesses strong expertise in GPU-accelerated inference, Kubernetes, and CI/CD. This position offers a competitive compensation package, including a base salary of $160-200k and a strong equity package. #J-18808-Ljbffr