Role OverviewEvaluate GPU/accelerator kernel development tasks for AI models, assess numerical correctness, and collaborate with AI research teams to improve model training and evaluation processes.
What You Will Do
Evaluate kernel tasks, assess numerical correctness, and provide written feedback; collaborate with AI research teams to improve model training and evaluation processes.
Why It Might Be a Fit
Must have 3+ years of experience with CUDA, Triton, NKI, or Pallas (JAX), strong understanding of numerical-correctness criteria, and experience with performance profiling and benchmarking.
Requirements
- 3+ years of experience with CUDA, Triton, NKI, or Pallas (JAX)
- Strong understanding of numerical-correctness criteria for kernels
- Experience with performance profiling and benchmarking (e.g., nsight, ncu)
- Familiarity with common compilation and runtime failure modes
- Experience with at least three kernel task types
]]>