Summary from listing
Modular is hiring an AI Runtime Engineer to own a runtime operating across CPU, GPU, and accelerator hardware, optimizing performance for AI models. The role involves runtime and cross-stack optimizations, vendor networking libraries, collaboration with compiler, kernel, serving, models, tooling, and infrastructure teams, and customer performance analysis. Candidates need at least two years of high-performance computing experience, C++ and complex software systems experience, and experience with CPU or GPU runtime optimizations and performance analysis. The role is based in Modular’s Edinburgh office with at least three days per week on-site, relocation assistance for eligible candidates, and an estimated base salary of £82,800 to £123,600 GBP.
