Skip to main content
Normal Computing

Compiler Backend Engineer

Normal Computing Mountain View, CA, United States Full-time 1 month ago
Embedded & Systems Software AI/ML Hardware

Originally posted October 20, 2026 by the employer.

About the role

As a Compiler Backend Engineer at Normal Computing, you will design and build custom compilation passes that map LLM inference directly onto proprietary hardware architectures executing inside memory. You will work across the compiler-hardware boundary, evaluating implementations against simulators, FPGA prototypes, and silicon.

What you'll do

  • Build code generation passes that transform lowered programs into executable instructions for non-standard hardware architectures.
  • Own scheduling and memory planning across hardware resources to optimize utilization and end-to-end latency for LLM inference.
  • Define fusion and dispatch strategies to minimize data movement across the execution pipeline.
  • Co-design the abstraction layer between the compiler and hardware by providing constraints to hardware architects during pre-silicon development.
  • Validate compiler optimizations using simulators, FPGA prototypes, and incoming silicon while maintaining a performance regression suite.
  • Collaborate with frontend compiler engineers on lowered program handoffs and determine partitioning between generated code and hand-tuned kernels.

What you'll need

  • Deep experience with compiler optimization or code generation for accelerators or non-CPU targets, including scheduling, tiling, fusion, or resource allocation.
  • Understanding of hardware architecture metrics such as memory bandwidth, compute utilization, and physical hardware constraints.
  • Demonstrated experience shipping compiler optimizations that directly improve measured performance metrics.
  • Experience developing software alongside evolving pre-silicon hardware targets, spanning simulation to bring-up.
  • Fluency in Python, along with familiarity with C, C++, or Rust.

Nice to have

  • Experience with PyTorch's compilation stack (TorchDynamo, FX, Inductor, torch.export) or ML compilers such as IREE, TVM, or XLA.
  • Experience compiling for in-memory, spatial, or non-von-Neumann compute targets.
  • Background in hardware design tools such as logic synthesis or place-and-route.
  • Experience building or using cycle-level or performance simulators to guide compiler optimization decisions.
  • Contributions to open-source compiler or kernel infrastructure such as PyTorch, Triton, TVM, MLIR, or LLVM.
  • Published or presented compiler or performance research at venues such as MLSys, ASPLOS, or CGO.

Skills: compiler backend, LLVM, MLIR, code generation, LLM inference

More semiconductor jobs: Mountain View jobs

Market context

Tracked in our index since 21 Oct 2026. This is our observation date, not the employer posting date. Specialty: Infrastructure/Platform Software (AI ML Hardware). 109 active roles in this specialty at 29 employers in our index, as of 18 Nov 2026.

How we counted: postings read from employer career sites. How we count

Normal Computing

Normal Computing

Apply now
Mountain View, CA, United States
On-site
Full-time
1 month ago

Share this job