Senior Machine Learning Platform Engineer — Model Hosting & MLOps

What you’d do

Build the infrastructure and MLOps workflows that move custom models from development into reliable production. Hands-on work hosting LLM inference on GPU infrastructure, including model serving, throughput, latency, and cost management. Full time. Found on the employer's careers page on Oct 6, 2026. Apply through the link.

You’ll need

• Hands-on LLM inference hosting on GPU infrastructure
• Production model serving experience
• MLOps pipeline development
• Managed throughput, latency, and cost