You will be a member of the Inference Enablement Team and part of the bigger PyTorch AI framework organization.

We build the foundational technology and frameworks that enable and optimize state-of-the-art model architectures on new hardware. We work with many different types of model architectures across Ads, Reels, Feed, Marketplace, IG, and GenAI. We support the enablement of models on all kinds of hardware as well, including CPU, GPU, and custom Silicon. We build the model publishing frameworks and platforms to accomplish this at scale for a large, broad set of models that are pushing the state of the art in Inference. Our work involves a blend of software systems and ML, and you'll have the opportunity to learn about how PyTorch works at a more in-depth level as well. We play an integral role in helping Meta ship the most important, state-of-the-art models for inference, including models with significant Ads Revenue gain, Reels Watch Time gain, all while saving multiple MegaWatts of power through our efficiency work.