Intern

Inferact is seeking a University of Waterloo co-op student to work on systems that power the vLLM AI inference engine, focusing on making AI inference faster, cheaper, and more reliable at scale. The role involves tackling real engineering problems across the vLLM stack, from model execution and low-level accelerator code to distributed serving and cloud platform development. You will collaborate with the creators and core maintainers of vLLM to ship production-ready code and tooling used by developers worldwide.