Remote job
Runtime Engineer - Kernelize
Job details
About this role
Role overview Build a scalable runtime layer for machine learning workloads running across a broad range of AI accelerator hardware. This role focuses on runtime engineering and Triton-based optimization, contributing to foundational software that enables models to use different accelerator platforms.
Responsibilities - Design and build runtime capabilities that can support multiple types of AI accelerators. - Help scale runtime support as hardware platforms and machine learning workloads vary. - Apply Triton to improve machine learning performance and optimization across accelerators. - Shape foundational runtime technology as it is developed from the ground up.
Requirements - Runtime engineering skills suited to building scalable systems. - Passion for machine learning optimization using Triton. - Interest in supporting a diverse range of AI accelerator hardware.
Benefits and work setup - The role is fully remote, with geographic location considered when setting compensation.