Job Description
About the Company
A next-generation AI startup with Silicon Valley roots is hiring a LLMOps Engineer in Toronto to design, deploy, and optimize large-scale LLM infrastructure powering AI-native semiconductor design tools. With $33M+ in funding and rapid growth, the company is scaling production-grade model serving systems from the ground up.
About the Role
As an LLMOps Engineer, you'll architect distributed inference pipelines, drive infrastructure automation, and deliver high-throughput, low-latency serving environments. This role is ideal for someone who thrives at the intersection of systems engineering, MLOps, and distributed AI - with direct impact on how cutting-edge models power the company's core product.
Responsibilities
- Design and implement production-ready LLM deployment pipelines on AWS and Kubernetes/EKS.
- Build and scale GPU-accelerated inference infrastructure for high availability, low latency, and cost efficiency.
Ready to Apply?
Take the next step in your AI career. Submit your application to Arcadia today.
Submit Application