Kernel Engineer
At Tilde Research, our mission is to build moonshot, applied interpretability solutions. We believe that by fundamentally understanding models, we can unlock paradigm shifts in throughput, performance, and safety. Our approach is to innovate across the entire stack, from uncovering the fundamental building blocks of model computation to enabling the precise steering of their behavior. We are driven by the conviction that true progress in interpretability will allow us to make AI more reliable and capable. About the role:As a Kernel Engineer at Tilde, you'll design, implement, and optimize high-performance GPU kernels that are critical to scaling our training and inference workloads. Your work will enable faster iteration cycles, higher throughput, and lower latency. You'll work closely with ML researchers and engineers to co-design models and infrastructure that are deeply performance-aware, and help push the limits of what current hardware can support. What you might work on:Design, develop, and tune custom GPU kernels for core model operationsWork with ML engineers to prototype and scale novel model architecturesContribute to system-wide efforts to improve efficiency and throughput, beyond just kernel-level optimizationsYou're a good fit if you:Have experience in deep learning or related research areasCommunicate clearly and effectively, both verbally and in writingCan come up with and evaluate research ideasAre able to learn quickly Apply to this Job