Staff Deployment Engineer

Groq delivers fast, reliable AI inference. Our LPU-based system powers GroqCloudTM, giving businesses and developers the speed and scale they need. Headquartered in Silicon Valley, we’re on a mission to make high-performance AI compute more accessible and affordable. When real-time AI is within reach, anything is possible.

Requirements

• Design, implement, and optimize large-scale multi-cluster Kubernetes deployments supporting mission-critical workloads.
• Build Kubernetes controllers and operators in Go to support continuous deployment strategies for model instances and production workloads.
• Implement advanced deployment patterns (blue/green, canary, progressive delivery) to ensure safe and reliable production rollouts.
• Drive GitOps practices using (and building on top of) Flux (preferred) or ArgoCD, ensuring reproducible, declarative, and auditable deployments.
• Inject observability into every deployment—leveraging Prometheus, VictoriaMetrics, Grafana, and OpenTelemetry for metrics, logging, and tracing.
• Architect automated rollback, health checks, and failover mechanisms to maximize uptime and deployment confidence.
• Operate and optimize deployments across multiple regions, clusters, and heterogeneous workloads.
• Partner with application, platform, and infrastructure engineers to align deployment best practices across the organization.
• Drive standards for deployment reliability, mentor peers on Kubernetes and GitOps practices, and raise the bar for automation across engineering.

Benefits

• Comprehensive compensation package
• Equity
• Benefits