ML Compiler Architect for LLM Accelerator Hardware

Neurophos; Sunnyvale, Austin (CA, TX); On-site; USD 140,000 - 200,000; Full time

Benefits offered by this job

Health plan premiums

Unlimited PTO

401(k) matching

Stock options

Voluntary benefits

Personalized benefits

Job summary

Neurophos is hiring an ML Compiler Engineer to lead compiler development for a novel LLM accelerator architecture in a full-time onsite role in the US. You will design toolchains, optimize graph and memory patterns, and integrate with PyTorch/JAX ecosystems.

The candidate should have a strong background in compilers and parallel computing, with experience across ML workloads and accelerator hardware. Join a world-class team building a photonics-based AI accelerator and contribute to end-to-end

Qualifications

• Master's degree in Computer Science or a related field.
• 5+ years of experience in compiler development.
• Expert-level proficiency in Python and C.
• Experience with hardware compilers.
• Familiarity with Large Language Model architectures and their computational requirements.
• Hands-on experience with compiler frameworks and code optimization techniques.
• Deep understanding of computer architecture, memory hierarchies, and parallel computing concepts.
• Experience with AI/ML accelerators (GPUs, TPUs, FPGAs) and their programming models.

Responsibilities

• Design and implement toolchains for our custom LLM accelerator architecture.
• Develop optimization strategies that bridge software algorithms to hardware implementations.
• Design and implement custom compiler components, including IR dialects, graph transformations, and lowering passes.
• Optimize computational graphs and memory access patterns for our hardware architecture.
• Integrate with existing ML frameworks (e.g., PyTorch, JAX, Triton).
• Build and maintain test infrastructure to ensure compiler correctness and performance.

Skills

Python

C

Parallel computing

AI accelerators

Graph transformations

PyTorch/JAX

Optimization

Education

Master's degree in Computer Science

PhD in CS (preferred)

Tools

LLVM/MLIR

GCC

CMake

Git

Docker

PyTorch

Job description

Neurophos is hiring an ML Compiler Engineer to lead compiler development for a novel LLM accelerator architecture in a full-time onsite role in the US. You will design toolchains, optimize graph and memory patterns, and integrate with PyTorch/JAX ecosystems.

The candidate should have a strong background in compilers and parallel computing, with experience across ML workloads and accelerator hardware. Join a world-class team building a photonics-based AI accelerator and contribute to end-to-end