MLIR Compiler Engineer for AI Hardware Backend Flexible PTO

Persimmons; San Jose (CA); On-site; USD 120,000 - 150,000; Full time

Benefits offered by this job

Competitive salary and benefits package

Flexible PTO

401k

Job summary

A cutting-edge AI infrastructure company in San Jose, CA seeks a Compiler Engineer to transform MLIR-based models for custom accelerator hardware. The successful candidate will develop compiler pipelines, design optimization techniques, and collaborate across teams to enhance AI hardware solutions. With strong focus on MLIR and compiler infrastructure, this role demands 5+ years experience in C++ and familiarity with Python. Competitive salary and flexible benefits await the right candidate.

Qualifications

• Solid understanding of MLIR framework principles and methods.
• 5+ years experience in C++ with clean code practices.
• Hands-on experience developing compiler infrastructure.

Responsibilities

• Develop MLIR-based compiler pipelines for custom hardware.
• Design efficient mid- and backend optimization techniques.
• Collaborate with teams to achieve optimal execution.

Skills

MLIR framework principles

C++ (5+ years experience)

Python

Loop optimization techniques

Register allocation

Tools

LLVM

PyTorch

Triton

Job description

A cutting-edge AI infrastructure company in San Jose, CA seeks a Compiler Engineer to transform MLIR-based models for custom accelerator hardware. The successful candidate will develop compiler pipelines, design optimization techniques, and collaborate across teams to enhance AI hardware solutions. With strong focus on MLIR and compiler infrastructure, this role demands 5+ years experience in C++ and familiarity with Python. Competitive salary and flexible benefits await the right candidate.