Senior GPU Kernel Engineer: ML & HPC Optimizer

Advanced Micro Devices; Austin, Northern (TX, KY); Hybrid; USD 210,000 - 300,000; Full time

Job summary

Advanced Micro Devices in Austin, TX seeks a highly skilled Fellow to define and lead end-to-end software optimization for premier GPU workloads. You will shape kernel performance, ML software stacks, and collaboration with customers to deliver high-value ROCm solutions.

The role emphasizes collaboration across architecture, compiler, and framework teams, with a strong focus on transformer-era models and cutting-edge ML techniques.

Qualifications

• Strong understanding of modern model architectures (Transformer, Attention, KV Cache) and optimization techniques like quantization, speculative decoding, and FlashAttention.
• Excellent GPU architecture knowledge, performance analysis, algorithm development, and machine learning experience.
• Proven history of optimizing GPU kernels with advanced algorithms across the AI software stack.

Responsibilities

• Define and drive the end-to-end software optimization strategy to achieve industry-leading performance for top-tier customers.
• Play a pivotal role in GPU architecture feature design, usage, API design, optimization, and deployment.
• Perform external benchmarking and research to define opportunities to improve GPU kernel performance on AI products.
• Collaborate with hardware, compiler, and framework teams to influence silicon features based on AI workloads.
• Communicate with customers and partners to improve ROCm applications, libraries, and tooling.

Skills

GPU kernel optimization

ML software development

Cross-functional collaboration

Performance analysis

Education

Bachelor’s/Master’s/PhD in CS/CE or equivalent

Job description

Advanced Micro Devices in Austin, TX seeks a highly skilled Fellow to define and lead end-to-end software optimization for premier GPU workloads. You will shape kernel performance, ML software stacks, and collaboration with customers to deliver high-value ROCm solutions.

The role emphasizes collaboration across architecture, compiler, and framework teams, with a strong focus on transformer-era models and cutting-edge ML techniques.