AMD is seeking a talented ML Inference Engineer who is passionate about pushing the boundaries of ML performance for Gaming and Generative AI. In this role, you’ll design, implement, and optimize high‑performance GFX kernels that power next‑generation visual and AI experiences across AMD’s product ecosystem. You’ll collaborate closely with hardware architects, software teams, and product groups to drive ML‑accelerated technologies into real customer applications.
responsibilities :
Transform neural network models and algorithms written in PyTorch/Onnx to efficient GFX shaders using languages such as HIP, Cuda, HLSL
Design, implement, and optimize high‑performance GPU kernels for ML operators.
Build AI‑driven automation tools to accelerate kernel generation and optimization workflows.
Analyze and debug performance bottlenecks in collaboration with compiler and performance modeling teams.
Stay up‑to‑date with advancements in GPU architecture, ML accelerators, rendering techniques, and ML/GFX frameworks.
Contribute to tools and methodologies for integrating optimized shaders into game engines.
Drive next‑generation features across hardware, drivers, and compilers with a focus on performance per watt and performance per area.
Document and share knowledge on best practices for GFX and ML programming within the team.
Participate in code reviews and provide constructive feedback to peers.
requirements-expected :
Strong programming skills in C++ and Python.
Hands‑on experience optimizing GPU kernels for ML workloads using frameworks like HIP, CUDA, OpenCL, or HLSL.
Deep understanding of GPU architecture: compute units, memory hierarchy, cache, scheduling, and the GPU programming model.
Experience with graphics APIs (DirectX, Vulkan, OpenGL) and shader programming.
Solid grasp of ML operators, their mathematical foundations, and modern ML architecture concepts.
Experience with concurrent programming and threading.
Development experience on Windows and/or Linux.
Familiarity with software tools such as CMake and GitHub.
Familiarity with low‑level GPU languages (e.g., PTX).
Understanding of ML techniques applied to graphics and rendering.
Strong communication, collaboration, and problem‑solving skills.
Bachelor’s or Master’s degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
