About me
Rob Suderman manages front-end support with AMD’s SHARK AI group with a goal of pushing tier one support for as many ML compute languages as possible. This has included core work on Torch-mlir, JAX, TOSA, and StableHLO, including being a founding team member on the IREE project. In the past he has performed research in Video Quality Analysis, GPGPU compute, and language model execution on compute constrained devices.