Belvedir is seeking a Member of Technical Staff, Infrastructure in San Francisco to build and operate the training and serving stack for custom models on Kubernetes, aiming for scalable distributed training, efficient batching, caching, routing, and autoscaling for latency-sensitive deployments.
You will drive down costs per token with quantization, speculative decoding, kernel work, and smarter scheduling while profiling end-to-end bottlenecks across GPU, CPU, network, or model components to
#J-18808-Ljbffr
We are seeking a motivated Staff ML Infra Engineer – LLM Training & Serving Kubernetes to join Belvedir (Fractal Machine Research, Inc.) in San Francisco, CA, United States.
All applications are reviewed carefully by our team.
The position is based in San Francisco, CA, United States.
This opportunity is part of our work in IT & Technology.
The advertised compensation is 180.000 - 240.000.