Sr. Staff Observability Engineer (GPU Cloud & Telemetry Platform)

Location: Seoul, South Korea

Company

hirify.global is a large global public e-commerce company building high-scale services for shopping, eating, and everyday life in South Korea.

What you will do

• Own the end-to-end observability platform for GPU-as-a-Service infrastructure, including Grafana Alloy, Mimir, Loki, and Vector.
• Architect low-latency, high-throughput telemetry pipelines for GPU metrics, Kubernetes and container telemetry, logs, and traces.
• Build Grafana dashboards for GPU fleet health, tenant usage, billing insights, capacity planning, and forecasting.
• Define GPU-specific SLIs, SLOs, error budgets, and predictive observability practices.
• Integrate observability with CI/CD and infrastructure-as-code pipelines using Terraform and Kubernetes, including automated canary analysis and rollbacks.
• Lead cross-layer incident forensics, design reviews, mentoring, open-source strategy, and secure multi-tenant telemetry architecture.

Requirements

• Extensive experience in observability, SRE, or distributed infrastructure.
• Proven experience building large-scale metrics and log telemetry pipelines.
• Strong knowledge of Grafana Alloy or the Prometheus ecosystem, Grafana Mimir or Cortex/Thanos, Grafana Loki, and Vector or similar log pipelines.
• Strong programming skills in Go or Python, plus experience with TSDBs and large-scale log storage.
• Experience with Kubernetes, Linux internals, bare-metal GPU clusters, and hybrid cloud environments.
• Experience with NVIDIA DCGM, the CUDA ecosystem, and high-performance networking such as RDMA or InfiniBand is required or preferred depending on the area.

Culture & Benefits

• Full-time regular employment with a 12-week probation period, which may be adjusted according to business needs.
• Entrepreneurial startup culture combined with the resources of a large public company.
• Opportunities to drive new initiatives, innovations, and hands-on technical impact.
• Focus on reliable, scalable infrastructure and proactive failure detection.

Hiring process

• Application review.
• First virtual interview followed by a second virtual interview.
• Offer; scheduling and process details may vary by role.