AI/ML Performance Intern — Hybrid, High-Impact Kernels

Waymo LLC; Mountain View (CA); Hybrid; USD 96,000 - 117,000; Full time

Benefits offered by this job

Hybrid onsite internship

Benefits programs

Job summary

Waymo LLC in Mountain View offers a hybrid onsite engineering internship focused on ML accelerators and DSLs. You will build high-performance, low-level kernels for a custom accelerator and validate their correctness and numerical accuracy.

Ideal candidates are MS or PhD students in CS/CE or related fields, with Python and/or C++ fluency and familiarity with CUDA/Triton/Gluon. Interns gain exposure to real-world hardware/software stacks and company benefits.

Qualifications

• MS/PhD candidate in CS/CE or related quantitative field.
• Experience using AI agents to improve coding performance.
• Knowledge of low-level ML accelerator kernels and performance analysis.
• Familiarity with CUDA/Triton/Gluon DSLs.

Responsibilities

• Develop high-performance kernels in a DSL for a custom ML accelerator.
• Ensure functional correctness and numerical accuracy of kernels.
• Conduct performance analysis to identify bottlenecks and improvements.
• Develop a harness to recursively improve kernel generation.

Skills

Python

C++

ML accelerators

Kernel development

Education

MS or PhD candidate in CS/CE/Computational Science

Tools

CUDA

Triton

Gluon

Job description

Waymo LLC in Mountain View offers a hybrid onsite engineering internship focused on ML accelerators and DSLs. You will build high-performance, low-level kernels for a custom accelerator and validate their correctness and numerical accuracy.

Ideal candidates are MS or PhD students in CS/CE or related fields, with Python and/or C++ fluency and familiarity with CUDA/Triton/Gluon. Interns gain exposure to real-world hardware/software stacks and company benefits.