WHAT YOU DO AT AMD CHANGES EVERYTHING 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_ THE ROLE: AMD is looking for an AI/Compute architect who is passionate about optimizing and benchmarking AI/ML model performance on AMD GPUs. You will work closely with the internal ROCm team and open source ML framework communities to enhance AI/ML model performance on AMD GPUs. You will be a member of the industry’s talented subject matter experts and will work with the very latest hardware and software technology. THE PERSON: Strong technical, analytical, and problem solving skills in identifying and optimizing performance bottlenecks of AI/ML models on AMD devices. Strong programming capabilities in C++/Python development in a Linux environment. Ability to work as part of a team, while also being able to work independently, define goals and scope and lead your own development effort. KEY RESPONSIBILITIES: Optimize the performance bottlenecks of the LLM and Diffusion model inference, pretraining, fine-tuning on multi-GPU and multi-node environments. Work closely with the internal ROCm team to enhance the competitiveness of the ROCm software stack to the latest AI/ML models Setup and run AI/ML model benchmark environment to identify the optimization directions of the ROCm software Collaborate and contribute to the ML open source communities like vLLM, TGI from Huggingface, PyTorch, etc. on AMD GPUs. Write technical documentations and share the competitiveness of the AMD GPUs and ROCm software stack PREFERRED EXPERIENCE: AI/ML knowledge and expertise - the latest NLP, RAG, and Vision model architecture Excellent C/C++/Python programming and software design skills, including troubleshooting, performance analysis, and model profiling. Experiences in writing CUDA kernels and OpenAI’s Triton kernels are plus Basic knowledge of using docker, ubuntu, git, shell scripting is a must ACADEMIC CREDENTIALS: Masters or PhD or equivalent experience in Computer Science, Computer Engineering, or related field LOCATION: Seoul, Korea #LI-JV1