AI Hardware Compiler Backend Engineer

Normal Computing Corporation; Palo Alto (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

Normal Computing is a pioneering AI hardware company building foundations for memory-bound AI workloads. As a Compiler Engineer focused on the backend, you will design and implement compilation strategies that map LLM inference to our custom hardware, balancing scheduling, memory planning, and data movement.

You will operate near the hardware boundary, validating improvements on simulators, FPGA prototypes, and silicon as it becomes available.

Qualifications

• Experience optimizing compilers for accelerators.
• Proven ability to generate efficient code for non-CPU targets.
• Strong scripting and systems programming skills.

Responsibilities

• Build passes turning lowered programs into hardware-executable code.
• Own scheduling and memory placement across hardware resources.
• Make fusion and dispatch decisions for LLM inference.
• Bridge compiler and hardware, feeding constraints to architects.
• Profiling and validation across simulators, FPGA, and silicon.
• Coordinate handoffs with frontend compiler engineers.

Skills

Compiler optimization

Code generation

Scheduling

Memory planning

Fusion/Dispatch

Python

C/C++/Rust

Tools

PyTorch

MLIR

LLVM

XLA

Job description

Normal Computing is a pioneering AI hardware company building foundations for memory-bound AI workloads. As a Compiler Engineer focused on the backend, you will design and implement compilation strategies that map LLM inference to our custom hardware, balancing scheduling, memory planning, and data movement.

You will operate near the hardware boundary, validating improvements on simulators, FPGA prototypes, and silicon as it becomes available.