Description
We are hiring a Senior AI Compiler Engineer to join our team. As a Senior AI Compiler Engineer, you will build an MLIR-based AI compiler that powers NVIDIA's inference engine end-to-end, with a focus on performance, fast builds, low memory use, and Ahead-of-Time and Just-in-Time usability across data center and edge.
Your responsibilities will include developing MLIR-based graph representations and optimizations for future GPU architectures, partnering with framework and hardware teams to enable new model patterns and upcoming GPU architectural features, defining APIs and MLIR dialects, conducting performance optimizations and analysis, implementing compiler optimizations and kernel generation for neural networks, and contributing to other general software engineering work.
To be successful in this role, you will need a Bachelor's, Master's, or Ph.D. in Computer Science, Computer Engineering, or a related field, or equivalent experience. You should have 3+ years of relevant work or research experience in performance analysis and compiler optimizations, experience with compiler technologies such as MLIR, XLA, and LLVM, excellent C/C++ and Python programming and software design skills, including debugging, performance analysis, and testing, and the ability to work independently, define project goals and scope, and lead your own development efforts.
Preferred qualifications include understanding of deep learning models, algorithms, and frameworks such as PyTorch and JAX, experience with GPU kernel generation targeting high performance and fast build times, proficiency in GPU architecture with CUDA or OpenCL programming experience, and a track record of mentoring early career engineers and interns.