Next-Gen AI Hardware and Systems

Job Description

xAI is seeking a highly motivated and skilled individual to join their team as an AI Hardware and Systems expert. This role involves co-designing next-generation AI systems in collaboration with xAI's partners, spanning from silicon to software compilers to models. The ideal candidate will be passionate about pushing the boundaries of computational efficiency and scalability in AI.

The role involves multiple levels of responsibility:

• Optimizing front-end compilers to transform training and inference workloads into compute graphs for new AI hardware, estimating their performance.
• Writing PTX-level or lower-level codes for critical kernels to maximize performance on cutting-edge microarchitectures.
• Designing and refining new hardware architectures to push the boundaries of computational efficiency.
• Leveraging AI-driven approaches to revolutionize software compiler development and hardware design processes.

Requirements for this role include:

• Proficiency in coding for accelerators, including CUDA, cutlass, HIP, ROCm, Triton, and other assembly languages or DSLs.
• Experience simulating training workloads on novel AI hardware architectures.
• Experience with compiler toolchain development and a deep understanding of the advantages and disadvantages of modular tools such as OpenXLA, MLIR, and LLVM.
• Hands-on experience with distributed training and/or high-QPS production inference.
• Deep understanding of the microarchitecture of AI accelerators and GPUs.
• R&D experience in using AI for software compiler and/or hardware design.

xAI offers:

• Opportunity to work on cutting-edge AI systems.
• Collaboration with a small, highly motivated team.
• A flat organizational structure that encourages initiative and excellence.