Staff Software Development Engineer - GPU Communication Libraries, SHMEM/MPI

About the position

We care deeply about transforming lives with AMD technology to enrich our industry, our communities, and the world. Our mission is to build great products that accelerate next-generation computing experiences - the building blocks for the data center, artificial intelligence, PCs, gaming and embedded. Underpinning our mission is the AMD culture. We push the limits of innovation to solve the world's most important challenges. We strive for execution excellence while being direct, humble, collaborative, and inclusive of diverse perspectives. AMD together we advance.

Responsibilities

• Design software modules in C++, Python, HIP, assembly to enable collective communication software for datacenter GPU systems
• Understand existing codebases and software designs, and make improvements to enhance maintainability and operational efficiency
• Work with AMD's architecture specialists to improve future products and plan software support strategies
• Aid management in planning, and delivering industry-leading software
• Stay informed of software and hardware trends and innovations, especially pertaining to software algorithms and hardware architecture
• Design and develop new groundbreaking AMD technologies
• Participate in new ASIC and hardware bring ups

Requirements

• Experience with agile software development practices
• Demonstrated capacity to technically lead developers of varying levels
• Proficient in C/C++ & Python programming employing best software design practices
• GPU software development involving HIP, CUDA, or OpenCL
• Experience with at least one of the following: Implementing communication middleware like MPI/SHMEM, Implementing lower-level communication frameworks like UCX and libfabric, or development using RDMA APIs, Development and optimization of communication collective algorithms (e.g. AllReduce), Experience in software performance evaluations, optimizations and debugging
• Ability to closely interact with software technical leads, program managers, and interface with hardware teams