River AI
Kernel Engineer (Custom Silicon), Hardware
$200K–$420K
Palo Alto, CA +3 · Full-time · Posted Jun 28, 2026
- Location
- Palo Alto, CA
Austin, TX
Austin, Texas, United States
Palo Alto, California, United States - Experience
- 5+ years of practical industry experience in low-level performance programming.
- Education
- Bachelor’s degree in Computer Engineering, Computer Science, Electrical Engineering, or a related field.
- Visa sponsorship
- River AI sponsors visas; it cannot guarantee success for every candidate or role.
About the job
Develop kernel-generation frameworks and optimize low-level deep learning operations for River AI’s custom silicon.
What you'll do
- Build C++ code-generation frameworks that emit optimized assembly for the custom ISA.
- Implement and tune deep learning kernels, including GEMM, attention, convolutions, and element-wise operations.
- Profile and validate performance while collaborating with compiler, architecture, and RTL teams on hardware/software co-design.
What they ask for
- Bachelor’s degree in Computer Engineering, Computer Science, Electrical Engineering, or a related field.
- 5+ years of practical industry experience in low-level performance programming.
- Proficiency in modern C++ and a strong understanding of hardware programming models, computer architecture, and deep learning primitives.
- Proven track record of shipping highly optimized kernels.
Nice to have
- Experience optimizing Tensor Cores, matrix multiply-accumulate units, or custom vector extensions.
- Experience with advanced C++ template metaprogramming, code-generation techniques, or low-level hardware profiling tools.
Pay
$200,000 - $420,000 USD annual salary (base salary)
Tools
C++, CUDA, Triton, CUTLASS, custom accelerator assembly, custom ISA assembly
AI focus
Develop and optimize compute kernels for deep learning operations on custom silicon.
Model-written summary · the original posting is authoritative