MTS Software Development Engineer

Advanced Micro Devices, Inc•Santa Clara, CA

About The Position

AMD, Inc. is hiring an MTS Software Development Engineer to architect and drive its AI software stack. The role establishes best practices and optimizes performance from low-level GPU kernels to large-scale distributed systems, shaping foundational software for AMD hardware. It uses large language models and agent-based technologies to accelerate development and performance improvements across the AMD ROCm ecosystem and supports demanding AI applications, including foundation models and autonomous AI agents. The position contributes to the full hardware-software co-design lifecycle, from influencing future GPU architectures to developing software for new accelerators and collaborating with the broader AI community. There are multiple openings. Travel is not required. A degree is required.

Requirements

Master’s degree or foreign equivalent in Computer Science, Computer Engineering, Electrical Engineering, Software Engineering, or a related field, and three years of experience in the job offered or a closely related engineering role; alternatively, a bachelor’s degree or foreign equivalent in one of these fields and five years of progressive post-baccalaureate experience in the job offered or a closely related engineering role.
At least two years of experience in software development in performance-critical environments.
At least two years of experience with deep learning model architectures, such as natural language processing, recommendation, computer vision, or other modern AI systems.
At least two years of experience optimizing deep learning model inference pipelines.
At least two years of experience with modern C++ and object-oriented design.
At least two years of experience with GPU programming (HIP or CUDA) and optimizing deep learning kernels and operators.
At least two years of experience with GPU architecture, memory hierarchy, and GPU profiling or performance analysis tools to diagnose and resolve complex bottlenecks in distributed, multi-GPU systems.

Responsibilities

Architect and drive the AI software stack, establishing best practices and optimizing performance from low-level GPU kernels to large-scale distributed systems.
Use large language models and agent-based technologies to accelerate development and improve performance of the AMD ROCm ecosystem.
Accelerate AI applications, including foundation models and autonomous AI agents.
Contribute to the hardware-software co-design lifecycle, including influencing future GPU architectures and developing software for new accelerators.
Collaborate with the broader AI community.