AMD is looking to develop next-generation GPU solutions for data centers and super-computers, requiring architecture exploration, modeling, and analysis of ML/HPC workloads to provide insights into new hardware and software technologies.
Requirements
- Knowledge in GPU architectures, basic knowledge of CPU architecture
- Background in Network-on-Chip (NoC) design and interconnect systems
- Experience in machine learning (ML) networks including TensorFlow and PyTorch
- Understanding of Graphics and Compute API's such as CUDA, OpenCL, and Vulkan
- Experience with operating systems (OS) and device driver development is a plus
- Strong programming foundation in C, C++, and scripting languages (Python, etc.)
- Experience in hardware modeling and design using RTL or SystemC
Responsibilities
- Engage in architecture exploration, modeling and analysis of ML/HPC workloads.
- Provide valuable insight into new and emerging hardware and software technologies and MI line of products.
- Identify complex technical problems, break them down, summarize possible solutions
- Work with architects to propose innovative solutions that can be implemented in HW, validated by developing various models/simulators
- Collect/summarize data or simulation results for consumption by architects and design teams
Other
- You have excellent analytical and problem-solving skills, along with attention to detail.
- You are an effective team player who focuses on collaboration, team building, mentoring, and furthering team success.
- You have strong communication, time management, and presentation skills
- Communicate and collaborate with a network of experienced architects and designers around the world.
- Undergrad degree required. Bachelor of Science, Masters, or PhD degree with emphasis in Electrical Engineering, Computer architecture, or Computer Science with relevant experience preferred
