AI Kernel & ML Accelerator Intern — Hybrid

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

Benefits offered by this job

Benefits programs

Job summary

Waymo seeks an intern to design and implement high-performance, low-level kernels for a custom ML accelerator using a domain-specific language. You will ensure numerical accuracy and performance, and build a harness to automate kernel generation.

Candidates should be enrolled in an MS or PhD program in a quantitative field and have experience with AI agents, kernel analysis, and DSLs like CUDA/Triton/Gluon. Hybrid onsite internship in Mountain View, CA.

Qualifications

• Currently enrolled in an MS or PhD program in Computer Science, Computer Engineering, Computational Science, or a related quantitative field.
• Demonstrated track record of using AI agents and harnesses to improve coding performance.
• Working knowledge of key kernels for transformer inference including performance analysis and optimization.
• Familiarity with one or more low-level ML accelerator DSLs (CUDA, Triton, Gluon, etc.).

Responsibilities

• Work with AI agents to create high performance low-level kernels in a Domain-Specific language for a custom ML accelerator.
• Ensure functional correctness and numerical accuracy of kernels.
• Conduct performance analysis of the kernels to identify performance bottlenecks and areas that need improvement.
• Develop a custom harness to recursively improve kernel generation and remove the need for human involvement.

Skills

AI agents

Kernel analysis

Python

C++

CUDA/Triton/Gluon

Education

MS or PhD program in CS/CE/Computational Science

Job description

Waymo seeks an intern to design and implement high-performance, low-level kernels for a custom ML accelerator using a domain-specific language. You will ensure numerical accuracy and performance, and build a harness to automate kernel generation.

Candidates should be enrolled in an MS or PhD program in a quantitative field and have experience with AI agents, kernel analysis, and DSLs like CUDA/Triton/Gluon. Hybrid onsite internship in Mountain View, CA.