Site Reliability Engineer (AI)

Location: Hybrid, Seoul, South Korea

Requirements

• Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
• Strong programming skills in one or more general-purpose languages such as Rust, Python, or Go.
• Solid understanding of operating systems, computer networks, and cloud-native or container-based environments.
• Experience improving production reliability through SLOs, observability, incident analysis, rollout safety, and error-budget-driven decisions.
• Experience designing or operating distributed systems where failures, overload, latency, and capacity limits must be explicitly managed.
• Ability to analyze technical problems and communicate clearly with engineering teams.

What you will do

• Define and evolve reliability goals through SLIs, SLOs, error budgets, and operational metrics.
• Design and build observability foundations covering metrics, logs, traces, dashboards, alerts, user impact, and failure modes.
• Analyze production systems across software, infrastructure, networking, and security boundaries, then drive architectural improvements.
• Improve rollout safety, capacity planning, load validation, graceful degradation, failure recovery, and incident learning.
• Build automation, internal tooling, and self-service workflows that reduce operational toil and improve engineering productivity.
• Operate and improve bare-metal Kubernetes clusters, cloud control planes, deployment pipelines, and API services running on Furiosa NPUs.

Culture & Benefits

• Full-time employment in a hybrid work arrangement.
• Work across production infrastructure, cloud-native systems, networking, observability, deployment, and AI accelerator services.