Software Engineer, Compiler, Scheduling and Optimization, Silicon

Google is seeking a Software Engineer to join their Silicon team, focusing on compiler optimization and scheduling for EdgeTPU. This role combines cutting-edge compiler technology with AI/ML performance optimization, making it an exciting opportunity for engineers interested in both compiler development and machine learning infrastructure.

The position involves working with Multi-Level Intermediate Representation (MLIR)-based compiler frameworks to optimize AI/ML workloads for Google's EdgeTPU hardware. You'll be responsible for developing core optimization and scheduling algorithms that are crucial for delivering optimal AI/ML performance to end users. This includes working on the latest Generative AI models and ensuring their efficient execution on Google devices.

The role offers a competitive base salary range of $141,000-$202,000, plus bonus, equity, and comprehensive benefits. You'll be working at either Mountain View, CA or Bellevue, WA, collaborating with talented teams across Google's hardware and software divisions.

Key responsibilities include improving compiler quality and performance, developing parallelization algorithms, optimizing compute and data movement costs, and working closely with hardware architects on next-generation EdgeTPU architectures. You'll also interact with product managers and researchers to stay ahead of Machine Learning trends and future use cases.

The ideal candidate should have at least 2 years of experience with software development, strong knowledge of data structures and algorithms, and significant experience with compiler optimizations and parallelization. Experience with MLIR, LLVM, or accelerator-based architectures is highly valued, as is familiarity with machine learning and generative AI architectures.

This position offers an opportunity to impact the future of AI hardware/software co-optimization at Google, working on technologies that will power the next generation of Google devices. You'll be at the forefront of compiler technology and AI acceleration, making this an excellent role for those interested in both low-level optimization and cutting-edge AI applications.