FuriosaAI
Software Engineer, Site Reliability Engineer
Seoul, Seoul, South KoreaPosted 5 days agofulltime
What you'd do
- Define and evolve SLIs,SLOs,and error budgets for production systems running on Furiosa NPUs
- Build observability foundations including metrics,logs,traces,dashboards,and alerts
- Analyze production reliability risks across software,infrastructure,and networking boundaries
What they want
- Strong programming skills in Rust,Python,C++,or Go
- Solid understanding of operating systems,computer networks,and container-based environments
- Experience with Kubernetes or cloud-native infrastructure
Nice to have
- Experience designing or operating distributed systems with explicit capacity and failure management
- Track record improving production reliability using error-budget-driven decision making
- Experience automating operational workflows to reduce toil