Senior Inference Engineer

Build and own the inference layer and production LLM serving pipeline at vCluster Labs. Deploy models to production on GPU infrastructure, operate serving frameworks (vLLM, SGLang, TensorRT-LLM), and optimize for scale using quantization, batching, caching, and routing. Implement real infrastructure in Python or Golang, partner with the CTO and Product to set the roadmap, and ensure low-latency, cost-effective serving. Required: production LLM serving experience, hands-on inference optimization, strong Python or Golang engineering skills, and clear communication. Bonus: Docker/Kubernetes, PyTorch/Transformers, CUDA/NCCL, DGX and NVIDIA Dynamo experience.