Teams at vCluster

Lead product direction for cloud-native GPU infrastructure and Kubernetes virtualization. Translate business priorities into technical specs, run alpha/beta validations, engage platform-engineer customers, define market positioning, and align engineering, sales, and marketing to ship and support scalable multi-tenant GPU platforms.

Lead design and implementation of a production-grade LLM inference platform: deploy and serve models on GPU infrastructure, optimize latency and cost with quantization/batching/caching/routing, build infrastructure in Python or Golang, operate serving frameworks (vLLM, SGLang, TensorRT-LLM), and own the inference roadmap working with CTO and Product.

Lead end-to-end application and product security for a Kubernetes-based multi-tenant platform. Perform deep security reviews of Go services, Kubernetes controllers, and frontends; lead threat modeling; integrate automated security checks into CI; manage vulnerability lifecycle; develop security-related features; and train developers on secure coding and attack vectors.