GPU Infrastructure Engineer

Together AI runs one of the largest open-source AI inference platforms. We are hiring GPU Infrastructure Engineers to build, optimize, and scale the compute layer powering inference for hundreds of millions of API calls.

You will work on Kubernetes orchestration, CUDA kernel optimization, distributed inference systems (vLLM, TensorRT-LLM), and GPU cluster management.

Requires deep Linux and CUDA experience, strong Python and Go skills, and ideally familiarity with large-scale ML serving.