Description
The MLOps Architect will design, build, and industrialize a low-latency, highly available model-serving platform for real-time predictive workflows. The role covers online inference architecture, production model servers, deployment patterns, autoscaling, performance profiling, monitoring, SLOs, CI/CD, and resilience across cloud and on-premises environments. The position is onsite in Charlotte, North Carolina, with a stated rate of $70 and requires expertise in Kubernetes, model serving, APIs, load testing, observability, and MLOps automation.
