1 day ago
San Jose, CA, USAIntern
Base Salary
$92k - $137k/yr
Responsibilities
- Optimize end-to-end AI model training and inference pipelines on AMD Instinct GPUs using ROCm and related frameworks.
- Explore model, kernel, operator fusion, scheduling, and accelerator design tradeoffs through rigorous benchmarking.
- Develop and evaluate quantization-aware, mixed-precision, and other AI model efficiency techniques.
- Build reproducible benchmarks and experiment harnesses, profile applications, identify bottlenecks, and deliver measurable improvements.
- Produce experimental reports and code artifacts suitable for internal repositories or open-source projects such as ROCm, Triton kernels, and PyTorch extensions.
Requirements
- Currently pursuing a PhD in Computer Science, Computer Engineering, Electrical Engineering, Applied Mathematics, or a related technical field.
- Demonstrated research or advanced project experience in AI systems, machine learning infrastructure, high-performance computing, computer architecture, or large-scale deep learning.
- Deep hands-on experience training, optimizing, or serving large-scale AI models with PyTorch or JAX and distributed training frameworks such as DeepSpeed, FSDP, or Megatron-LM.
- Strong experience with GPU performance engineering, kernel optimization, and accelerator programming using CUDA, HIP, Triton, or related technologies.
- Understanding of GPU architecture concepts including memory hierarchies, tensor cores/MFMA, operator fusion, and scheduling.
- Experience with profiling, benchmarking, performance modeling, and roofline analysis for evaluating utilization and bottlenecks.
- Expertise in quantization, low-precision formats, mixed-precision training, speculative decoding, and energy-efficient AI training and inference, with the ability to build rigorous reproducible experiments.
Benefits
- Full-time, 40-hour-per-week onsite internship in San Jose, California.
- Summer 2027 internship dates are May 24-August 13, 2027 for semester schools or June 21-September 10, 2027 for quarter schools.
- AMD benefits are described through its benefits-at-a-glance information.
Tech Stack
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.