Jobs

Inferact is seeking a Member of Technical Staff, Kernel Engineering to join their team in Singapore. This performance engineer will be responsible for writing kernels and low-level optimizations to make vLLM the fastest AI inference engine globally, working with various accelerator types and hardware vendors. The ideal candidate will have deep experience with CUDA kernels, a strong understanding of GPU architecture, and proficiency in C++ and Python for high-performance coding. This role is crucial for accelerating AI progress by making inference cheaper and faster, directly impacting vLLM's mission.