GPU Kernel Engineer — Accelerate AI Training & Inference

River AI Inc.; Palo Alto (CA); On-site; USD 200,000 - 420,000; Full time

Benefits offered by this job

Health insurance

Dental insurance

Vision insurance

Unlimited PTO

Relocation assistance

Visa sponsorship

Job summary

River AI Inc. is seeking exceptional GPU kernel engineers to accelerate training and inference for large models, building compute primitives, attention, matmul, and low-precision kernels.

You’ll own performance-critical ops, optimize memory, validate correctness, and collaborate with researchers and systems engineers to bring improvements into production, enabling faster, more efficient AI workloads.

Qualifications

• Bachelor's degree in Computer Science, Computer Engineering, or equivalent practical experience.
• Experience optimizing GPU kernels with CUDA, Triton, CUTLASS, CuTe, or comparable tools.
• Strong understanding of GPU architecture, memory hierarchies, and parallel execution.
• Proficiency in C++ and Python.
• Strong foundations in linear algebra, floating-point arithmetic, and numerical computing.
• Strong debugging and profiling skills, with a collaborative approach to engineering.

Responsibilities

• Build fast GPU kernels for attention, matrix multiplication, expert routing, and related operations.
• Optimize memory access, tiling, and synchronization to use GPU hardware efficiently.
• Develop FP8, FP4, and mixed-precision kernels while preserving numerical correctness.
• Accelerate fine-tuning and RL through optimized adapters, backward passes, and fused operations.
• Profile real workloads and integrate improvements into training and inference runtimes.
• Build reproducible benchmarks that verify correctness, gradients, and performance.

Skills

GPU kernel optimization

C++ programming

Python programming

Profiling & debugging

Numerical computing

Education

Bachelor's degree in CS/CE or equivalent

Tools

CUDA

Triton

CUTLASS

CuTe

PyTorch

vLLM

Job description

River AI Inc. is seeking exceptional GPU kernel engineers to accelerate training and inference for large models, building compute primitives, attention, matmul, and low-precision kernels.

You’ll own performance-critical ops, optimize memory, validate correctness, and collaborate with researchers and systems engineers to bring improvements into production, enabling faster, more efficient AI workloads.