4 days ago
Austin, TX, USAIntern
Responsibilities
- Develop, benchmark, and optimize AI software for training, fine-tuning, and inference across CPU, GPU, and accelerator platforms.
- Profile AI workloads, identify hardware and software bottlenecks, and implement performance improvements across compute, memory, communication, framework, and runtime layers.
- Design and optimize GPU or CPU kernels using HIP, CUDA, OpenCL, Triton, or related accelerator programming models.
- Research and implement model optimization methods including quantization, low-precision inference, sparsity, pruning, distillation, and parameter-efficient fine-tuning.
- Contribute to AI frameworks, libraries, execution runtimes, deployment technologies, compilers, graph optimization, and runtime systems.
- Develop or evaluate parallel and distributed computing methods, including collective communication and scalable training or inference techniques.
- Build automated evaluation systems, containerized development environments, CI/CD pipelines, internal tools, and developer productivity solutions.
- Collaborate with software engineers, researchers, architects, platform teams, and project stakeholders.
Requirements
- Currently enrolled in a U.S.-based PhD program in Computer Science, Computer Engineering, Artificial Intelligence, Machine Learning, Electrical Engineering, or a related technical field.
- Programming experience in Python and/or C/C++.
- Experience with one or more AI frameworks or runtimes, such as PyTorch, TensorFlow, JAX, ONNX Runtime, vLLM, or SGLang.
- Experience, coursework, research, project work, or strong technical interest in AI optimization, GPU kernels, AI frameworks, compilers, performance analysis, parallel or distributed computing, MLOps, DevOps, automated evaluation, CI/CD, containerized environments, or AI-assisted coding.
- Familiarity with development and build tools such as Git, CMake, Make, Conda, or Docker.
- Research publications, preprints, open-source contributions, or participation in the AI and machine learning developer community are preferred but not required.
Benefits
- Full-time, 40-hour-per-week hybrid or onsite work in Austin, Texas, for the duration of the term.
- Available 2027 terms include Spring/Summer Co-op from January 25 to August 13, Summer Internship from May 24 or June 21 to August 13 or September 10, and Summer/Fall Co-op from May 24 or June 21 to December 10.
- AMD benefits are offered as described in the company benefits materials.
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.