Forward Deployed Engineer (Staff)

What you'll do

• Write production code and build prototype integrations directly in customer environments to resolve technical blockers.
• Architect, deploy, and maintain production-grade vSphere Kubernetes Service (VKS) clusters for general compute and GPU workloads.
• Lead the migration of large-scale bare metal environments and legacy data stacks to cloud-native Kubernetes targets.
• Deploy and scale AI inference workloads, RAG architectures, and vector search frameworks using virtualized GPU resources.
• Containerize and migrate stateful engines, message brokers, and distributed caches onto Kubernetes platforms.
• Translate field-tested code and customer pain points into prioritized feature requirements for the core engineering team.
• Troubleshoot live networking, storage, and GPU failures in production environments to ensure successful platform adoption.
• Manage infrastructure as code using Terraform, Helm, and GitOps tools like ArgoCD or Flux.

What we're looking for

• Must have at least 12 years of related experience or a Bachelor's degree.
• Experience in Kubernetes, platform modernization, large scale stateful workload migration, and enterprise AI infrastructure.
• Hands-on experience operating GPU accelerated Kubernetes nodes and model serving runtimes like vLLM, TGI, and Triton Inference Server.
• Expertise in vector databases (Milvus, Qdrant, Pgvector) and distributed AI orchestration using Ray or KubeRay.
• Experience containerizing and operating high throughput systems including Redis, Kafka, RabbitMQ, and Spark.
• Proficiency with Infrastructure as Code and GitOps tools including Terraform, Helm, Kubernetes Operators, and ArgoCD.
• Technical depth in multiple Kubernetes distributions such as OpenShift, EKS, GKE, AKS, or Rancher.
• Ability to translate field requirements into product specifications for core engineering teams.