Waymo
2027 Summer Intern, BS/MS/PhD, AI-driven ML Performance Engineering Intern
Mountain View, CA, USA +1 · Internship · Posted Oct 1, 2026
- Location
- Mountain View, CA, USA
Mountain View, California, United States - Education
- Currently enrolled in a BS, MS, or PhD program in Computer Science, Computer Engineering, Computational Science, or a related quantitative field.
About the job
Develop and optimize low-level kernels for Waymo’s custom ML accelerator, using AI agents and a custom harness to improve kernel generation and performance.
What you'll do
- Create high-performance kernels in a domain-specific language and ensure their functional correctness and numerical accuracy.
- Analyze kernel performance to identify bottlenecks and improvements.
- Develop a custom harness to iteratively improve kernel generation and reduce human involvement.
What they ask for
- Currently enrolled in a BS, 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 transformer inference kernels, including performance analysis and optimization.
- Familiarity with one or more low-level ML accelerator DSLs, such as CUDA, Triton, or Gluon.
Nice to have
- Solid understanding of modern inference accelerator architectures.
- Fluency in Python and/or C++; working knowledge of ML numerical formats and their accuracy-performance tradeoffs.
Pay
$60—$60 USD (base hourly pay, Bachelors); $70—$70 USD (base hourly pay, Masters); $85—$85 USD (base hourly pay, PhD)
Tools
CUDA, Triton, Gluon, Python, C++
AI focus
Use AI agents to create and optimize accelerator kernels; develop a harness to iteratively improve kernel generation and reduce human involvement.
Model-written summary · the original posting is authoritative