Platform SRE - AI/GPU Observability & Reliability (Remote)

Pinnacle Talent Placement is seeking a Platform Site Reliability Engineer (SRE) to enhance reliability and observability in AI platforms. This remote position requires expertise in Linux, Kubernetes, and monitoring tools like Prometheus and Grafana.

The ideal candidate should have 3-6 years of experience with production support and incident response, along with strong automation skills using Bash or Python. Collaboration is key as you'll work with various teams to boost service reliability.