1 day ago
Santa Clara, Cuba or San Jose, CA, USAIntern
Responsibilities
- Develop an individual project to optimize LLM or VLM execution on the Ryzen AI NPU.
- Profile runtime and memory behavior, identify performance bottlenecks, and propose system optimizations.
- Write and tune AIE kernels with IRON for GEMM, attention, normalization, and activation operators.
- Analyze transformer execution on tiled dataflow accelerators and distinguish compute-bound from memory-bound behavior.
- Present findings to the wider engineering organization and document results for future team use.
- Work with a mentor who reviews progress weekly.
Requirements
- Be completing a PhD in Computer Science, Computer Engineering, or Electrical Engineering.
- Have strong knowledge of LLM and VLM architectures, including attention, KV cache, prefill versus decode, and vision encoder fusion.
- Have experience with compiler concepts such as graph lowering, operator fusion, scheduling, tiling, and memory planning.
- Be strong in Python and C++ and comfortable profiling code to distinguish compute-bound from memory-bound behavior.
- MLIR experience is a plus.
- Familiarity with AMD AI Engine architecture or experience writing kernels or dataflow designs with IRON is a plus.
Benefits
- Full-time, 40-hour-per-week hybrid or onsite work in San Jose or Santa Clara, California.
- Internship and co-op terms are available from January 25, 2027 through December 10, 2027, depending on the program and academic calendar.
- Mentorship with weekly work reviews and opportunities to present findings to the engineering organization.
- AMD benefits are described in the company’s benefits-at-a-glance materials.
Categories
About AMD
AMD designs and sells CPUs, GPUs, and adaptive/embedded computing products for PCs, data centers, gaming, and edge devices. Its portfolio includes Ryzen and EPYC processors, Radeon and Instinct graphics, and adaptive SoCs from its Xilinx acquisition, sold to OEMs, cloud providers, and device makers. Founded in 1969 and headquartered in Santa Clara, it is a public company on NASDAQ and supplies semi-custom chips for major game consoles.