GPU ML Architect

Samsung Electronics America Inc•San Jose, CA

47d

About The Position

Samsung, a world leader in advanced semiconductor technology, is founded on a simple philosophy - the endless pursuit of excellence will create a better world for all. At Samsung Austin Research and Development Center (SARC) and Advanced Computing Lab (ACL), we are building a center of excellence for Intellectual Property (IP) that is applied to high-performance computing devices (mobile, automotive, and other custom market segments) consumed by millions of people around the world. Come build with us! We are seeking a highly skilled GPU ML Architect to join our GPU Architecture hardware team. As a GPU ML Architect, you will be responsible for designing and developing innovative machine learning (ML) solutions for graphics processing units (GPUs). While knowledge of graphics or GPU architecture is not a requirement, a strong understanding of compute architectures and machine learning principles is essential. You will work closely with cross-functional teams to analyze workloads, model performance, and create new features for large vision models and image classification applications.

Requirements

15+ years of experience with a Bachelor's degree in Computer Science/Computer Engineering/relevant technical field, or 13+ years of experience with a Master's degree, or 11+ years of experience with a PhD
Strong understanding of machine learning principles and architectures
Experience with compute architectures and performance optimization
Experience with workload analysis and modeling
Excellent programming skills in languages such as C++, Python, or similar
Familiarity with LLMs, LVMs, and image classification
Ability to write clear and concise technical specifications
Strong analytical and problem-solving skills

Nice To Haves

GPU architecture and graphics pipeline experience is a big plus
Knowledge of ML frameworks and tools (e.g., TensorFlow, PyTorch) preferred

Responsibilities

You write technical specifications for new ML features and architectures, ensuring they integrate seamlessly with the graphics pipeline and meet performance, power, and functionality requirements.
You work on improving middleware to enhance the overall performance and efficiency of ML workloads on GPUs.
You create new hardware features and optimizations to improve PPA on ML applications such as LLMs, LVMs, Image Classification, etc.
You integrate with the graphics pipeline team to ensure that ML solutions are aligned with the overall graphics architecture.
You optimize GPU architectures for ML workloads, ensuring maximum performance and power efficiency.
Collaborate with engineers to analyze and model workloads, identifying performance bottlenecks and areas for optimization.