GenAI Inference Optimization Lead — GPU Performance

Advanced Micro Devices; San Jose (CA); Hybrid; USD 150,000 - 200,000; Full time

Job summary

A leading technology company is looking for a Principal GenAI Inference Optimization Engineer in San Jose, CA. This role will focus on optimizing performance and efficiency of generative AI on AMD GPU platforms. The ideal candidate will have significant expertise in GPU architecture, GenAI optimization techniques, and performance tuning tools. You will work across various layers and collaborate with cross-functional teams to drive impactful optimizations. This position is hybrid and offers a dynamic work environment.

Qualifications

• Solid understanding of GPU architecture and performance fundamentals.
• Hands-on experience with techniques for GenAI inference optimization.
• Experience working on LLM or multimodal inference workloads.

Responsibilities

• Optimize performance of GenAI inference workloads on AMD GPU platforms.
• Improve latency, throughput, and cost efficiency for model serving in production.
• Analyze and resolve bottlenecks across compute and memory systems.

Skills

GPU architecture understanding

GenAI inference optimization

Python

C++/CUDA/HIP

Performance tuning tools

ML frameworks (PyTorch, JAX, TensorFlow)

Education

B.S., M.S. or Ph.D. in Computer Science/Computer Engineering

Tools

Profiling/debugging tools

Inference/serving frameworks (vLLM, SGLang, Triton)

Job description

A leading technology company is looking for a Principal GenAI Inference Optimization Engineer in San Jose, CA. This role will focus on optimizing performance and efficiency of generative AI on AMD GPU platforms. The ideal candidate will have significant expertise in GPU architecture, GenAI optimization techniques, and performance tuning tools. You will work across various layers and collaborate with cross-functional teams to drive impactful optimizations. This position is hybrid and offers a dynamic work environment.