Normal Computing
Compiler Backend Engineer
$200K–$300K
Mountain View +1 · On-site · Full-time · Posted Oct 20, 2026
- Location
- Mountain View
New York
About the job
Build the custom compiler backend that maps large-model inference onto Normal Computing’s in-memory hardware, optimizing code generation, scheduling, and memory use.
What you'll do
- Develop code-generation passes, scheduling, memory planning, fusion, and dispatch for LLM inference.
- Co-design compiler abstractions with hardware architects and validate optimizations using simulators, FPGA prototypes, and silicon.
- Maintain performance regression testing and coordinate with frontend engineers on compiler-generated operations versus hand-tuned kernels.
What they ask for
- Deep experience in compiler optimization or code generation for accelerators or other non-CPU targets.
- Comfort working close to hardware, including memory bandwidth and utilization.
- Track record of shipping optimizations that improve measured performance.
- Fluency in Python and familiarity with C, C++, or Rust.
Nice to have
- Experience with PyTorch’s compilation stack or other ML compilers.
- Experience with non-von-Neumann compute, hardware design tools, performance simulators, or open-source compiler infrastructure.
Pay
$200K – $300K USD base salary
Tools
Python, C, C++, Rust, TorchDynamo, FX, Inductor, torch.export
AI focus
Compile and optimize LLM inference for custom in-memory hardware.
Model-written summary · the original posting is authoritative