Location
buenos aires, ciudad autónoma de buenos aires, Argentina
Posted
July 19, 2026
Job Description
Dialpad is expanding its AI Inference Platform Engineering team to build production systems that serve in-house AI models at scale, running on NVIDIA GPUs in GCP. This role is not a research or generic MLOps position but focuses on the machinery of inference, including model serving and runtime optimization.
You will work on deployment safety, traffic management, benchmarking, and observability to deliver low-latency, reliable inference services.
#J-18808-Ljbffr