site reliability engineer for generative media

fal is a generative media ecosystem that provides infrastructure, tools, and model access for teams building AI products. Its unified platform brings together high-performance inference, orchestration, and observability to help developers and enterprises bring generative media products from idea to production at scale.

• Own and operate Kubernetes infrastructure, including cluster lifecycle, upgrades, networking, and multi-tenant isolation for customer workloads
• Build and maintain CI/CD pipelines and deployment infrastructure
• Use AI extensively to automate production issue analysis and resolution and improve software development speed, reliability, and maintainability
• Build dashboards, alerting, and anomaly detection across systems
• Define and enforce SLOs and develop incident response processes
• Manage and improve networking, load balancing, and service mesh configurations
• Drive reliability improvements across the stack through automation, runbooks, and chaos engineering

• 5+ Years of experience managing critical production systems and software development workflows
• Strong production experience setting up and operating Kubernetes at scale, using infrastructure-as-code such as Terraform or Ansible
• Deep knowledge of Linux networking, container networking (CNI plugins, VXLAN, BGP), and DNS
• Experience building CI/CD systems and GitOps workflows such as FluxCD or ArgoCD
• Proficiency in Python and either Go or Bash for tooling and automation
• Strong experience with logging, monitoring, and alerting tools such as Prometheus, Grafana, Loki, Thanos, VictoriaMetrics, or Datadog
• Excellent communication skills and ability to drive technical decisions across teams
• Self-starter who executes quickly, takes ownership, and constantly seeks improvement
• Будет плюсом: experience managing GPU and AI/ML workloads, kernel-based monitoring and routing (eBPF, XDP), security tooling (Falco, Coroot, SIEM), bare metal Kubernetes networking (Calico, Cilium, MetalLB), distributed storage systems (Ceph, Longhorn, etc.)

• Interesting and challenging work
• Learning and growth opportunities
• Regular team events and offsites