Design and implement instrumentation pipeline collecting token usage,costs,models,latency,errors from multiple AI tools.
Build dashboards,automated alerts,and anomaly detection systems for real-time daily usage and cost visibility.
Design and operate centralized AI gateway managing authentication,permissions,rate limits,budgets,routing,caching,retry logic.
What they want
5+ years in infrastructure,platform,backend,or engineering building and operating production environments.
Hands-on AWS and Kubernetes experience building and operating real services with Infrastructure as Code tools like Terraform.
Production service development capability in Python or Go (not just operational tools).
Nice to have
Experience building LLM APIs,AI gateways,model serving,or internal platforms for AI coding tools.
Experience building and operating observability platforms with OpenTelemetry,Prometheus,Grafana,Loki,Tempo.
Technical experience in FinOps,cost attribution,internal chargeback systems for cloud and AI costs.
Seoulstart's read
Visa tier (likely)
F-2 / F-4 / F-5 / F-6 holders welcome
Korean language
Korean not required
English friendliness
High: JD in English, foreign-friendly signals
Context
Foreign-invested AI startup with Seoul as core R&D hub; global team structure suggests English-primary technical collaboration; no explicit Korean requirement signals visa sponsorship likely available for E-7 or F-series candidates with relevant infrastructure expertise.
This is Seoulstart's analysis of the public job description, not the employer's stated policy. Verify visa sponsorship, language requirements, and remote allowances directly with the recruiter.