Description
River is hiring a Kernel Generation Engineer to build the foundational compute engine for its custom silicon. The role develops C++ code-generation frameworks and meta-programming toolchains that emit optimized low-level assembly for deep learning operations such as GEMMs, FlashAttention, and custom activations. Responsibilities include low-level compute optimization, microarchitectural tuning, memory-hierarchy management, hardware/software co-design, and performance profiling and validation. The position is based in Austin, Texas or Palo Alto, California, offers $200,000–$420,000 USD plus equity, and includes visa sponsorship and health, dental, and vision benefits.
