Frontend ML Compiler Engineer for LLMs & AI Hardware

Normal Computing Corporation; Palo Alto (CA); On-site; USD 190,000 - 250,000; Full time

Job summary

Normal Computing seeks a Compiler Engineer focused on frontend and model bring-up to extend our IR, ops, and lowering passes for new LLM architectures. You will validate bring-up against simulators and FPGA prototypes, ensuring models are ready for silicon arrival.

This is a research-adjacent role requiring literature engagement and publishing on behalf of Normal. You will bridge compiler work to hardware-era deployment and serve models from compiler support to production.

Qualifications

• Hands-on ML compiler experience with shipped passes.
• Deep familiarity with PyTorch internals, including TorchDynamo, FX, torch.export.

Responsibilities

• Model Bring-up: add frontend and mid-level support for new LLM architectures in our compiler.
• IR and Lowering: extend IR/ops/lowering with full architectural fidelity and tests.
• Quantization and Numerics: represent quantization schemes and numeric formats for accuracy.
• Architecture Tracking: monitor LLM architecture landscape to guide bring-up priorities.
• Cross-Team Handoffs: hand lowered programs to backend compilers and LLM serving engineers.

Skills

ML compiler

PyTorch internals

LLM architectures

architecture bring-up

compiler infrastructure

Python, C++, Rust

Tools

IREE

XLA

TVM

Job description

Normal Computing seeks a Compiler Engineer focused on frontend and model bring-up to extend our IR, ops, and lowering passes for new LLM architectures. You will validate bring-up against simulators and FPGA prototypes, ensuring models are ready for silicon arrival.

This is a research-adjacent role requiring literature engagement and publishing on behalf of Normal. You will bridge compiler work to hardware-era deployment and serve models from compiler support to production.