Software Engineer, Compiler, Scheduling and Optimization, Silicon

Google is seeking a Software Engineer specializing in compiler optimization and scheduling for their EdgeTPU team. This role focuses on developing next-generation compiler technologies that will enhance AI/ML performance on Google's silicon platforms. The position requires expertise in compiler development, optimization algorithms, and machine learning systems.

The role involves working with cutting-edge technology, specifically the Multi-Level Intermediate Representation (MLIR)-based compiler framework, which serves both production and hardware/software codesign needs for EdgeTPU. The successful candidate will be responsible for designing and implementing optimization algorithms and compiler transformation frameworks to enable production-quality compilation of workloads.

This is an exciting opportunity to make a direct impact on hardware/software co-optimization of AI/ML use cases for current and future generations of Google devices, including the latest Generative AI models. The position offers competitive compensation ($141,000-$202,000) plus bonus, equity, and comprehensive benefits.

The ideal candidate should have at least 2 years of experience in software development, particularly with C++ or Python, and strong knowledge of compiler optimizations and parallelization. Experience with MLIR, LLVM, and machine learning architectures is highly valued. This role combines technical expertise with collaborative work, as you'll be working closely with EdgeTPU architects, product managers, and researchers.

Working at Google means joining a team that combines the best of Google AI, Software, and Hardware to create radically helpful experiences. The company's mission to organize the world's information and make it universally accessible and useful drives all aspects of their work. This role offers the opportunity to be at the forefront of AI technology development while working with some of the industry's best minds.