AI Inference Platform Engineer — Real‑Time, GPU‑Driven

Dialpad is seeking an AI Systems Engineer in Buenos Aires, Argentina to build production AI inference systems at scale. The role focuses on translating trained models into reliable, observable services running on NVIDIA GPUs in GCP.

It is a hands-on, implementation-heavy role at the intersection of model development and cloud infrastructure. You will shape the deployment and observability of model-serving platforms, optimize GPU utilization, and collaborate across teams to deliver scalable,