Machine Learning for Systems Researcher (Wave Language Team)

AMD is building Wave Language, a fundamentally new programming language for authoring high performance machine learning kernels on AMD GPUs and the rest of our hardware portfolio.

We are seeking a Machine Learning for Systems Researcher to explore and apply ML techniques to enhance the Wave Language ecosystem. Responsibilities include researching and developing ML-based approaches for compiler optimizations (e.g., phase ordering, code generation heuristics), performance modeling and prediction for AMD hardware, and potentially auto-tuning of kernels or system parameters. You will collaborate with compiler and performance teams to integrate successful research into the product.

The ideal candidate will have deep domain expertise at the intersection of machine learning and computer systems (MLSys). Required qualifications include at least 5 years of relevant research experience (PhD or equivalent), and a strong publication record in relevant conferences (e.g., MLSys, NeurIPS, ICML, ASPLOS, ISCA, CGO). Experience with compiler technology and performance analysis is a significant plus.