2027 PhD AI Systems & GPU Performance Engineering Intern

We will involve you in profiling, benchmarking, and optimizing AI training and inference workloads using ROCmTM, PyTorch, JAX, vLLM, Triton, and related performance engineering tools, helping identify bottlenecks across compute, memory bandwidth, communication, and kernel execution.

Your responsibility will include developing reproducible benchmarking frameworks and automation scripts that enable performance validation across AI models, software stacks, runtimes, drivers, and accelerator platforms.

We will train you to analyze and optimize end-to-end AI workflows, including large language models (LLMs) and generative AI applications, exploring techniques such as model optimization, operator fusion, scheduling strategies, mixed precision, and quantization.

You will work closely with engineers and researchers to evaluate GPU performance, compare workload characteristics across hardware and software environments, and contribute data-driven recommendations that improve efficiency, scalability, throughput, latency, and overall system utilization.

You get to explore cutting-edge AI systems research on AMD's newest hardware platforms while contributing profiling analysis, performance investigations, and optimization solutions that advance next-generation AI training and inference technologies.

Currently pursuing a PhD in Computer Science, Computer Engineering, Electrical Engineering, Applied Mathematics, or a related technical field, with an expected graduation date after the internship concludes.

Hands-on programming experience in Python and C/C++, with exposure to accelerator programming technologies such as CUDA, HIP, Triton, or similar frameworks.

Experience with deep learning frameworks such as PyTorch, JAX, or TensorFlow and familiarity with large-scale AI model training and inference concepts.

Experience working in Linux environments, including scripting, debugging, profiling, and performance analysis.

Exposure to GPU architecture concepts such as memory hierarchy, parallel execution, kernel optimization, communication efficiency, operator fusion, scheduling, or accelerator performance characteristics through research, coursework, or projects.

Familiarity with profiling, benchmarking, and performance analysis methodologies using tools such as rocProfiler, ROCm Systems Profiler, Omniperf, Nsight, or equivalent technologies.

Interest or experience in AI model optimization techniques such as quantization, mixed precision, distributed training, model serving, or large language model performance optimization.

Note: By submitting your application, you are indicating your interest in AMD intern positions. We are recruiting for multiple positions, and if your experience aligns with any of our intern opportunities, a recruiter will contact you.

This role is not eligible for visa sponsorship.

Benefits offered are described: AMD benefits at a glance.

AMD does not accept unsolicited resumes from headhunters, recruitment agencies, or fee-based recruitment services. AMD and its subsidiaries are equal opportunity, inclusive employers and will consider all applicants without regard to age, ancestry, color, marital status, medical condition, mental or physical disability, national origin, race, religion, political and/or third-party affiliation, sex, pregnancy, sexual orientation, gender identity, military or veteran status, or any other characteristic protected by law. We encourage applications from all qualified candidates and will accommodate applicants’ needs under the respective laws throughout all stages of the recruitment and selection process.

AMD may use Artificial Intelligence to help screen, assess or select applicants for this position. AMD’s “Responsible AI Policy” is available here.

This posting is for an existing vacancy.