Jobs

Inferact, founded by the creators of vLLM, is seeking an exceptional and autonomous Generalist Engineer to work across the entire vLLM stack, from low-level GPU kernels to high-level distributed systems. This globally remote role involves optimizing CUDA kernels, designing distributed orchestration, and implementing new model architectures, directly impacting AI inference worldwide. Candidates should have deep expertise in areas like systems programming, GPU/accelerator programming, or ML infrastructure, and thrive in a self-directed environment with strong asynchronous communication skills. Join us to accelerate AI progress by making inference cheaper and faster.