Google is seeking a Machine Learning Compiler Software Engineer to join their TPU Horizontal Scaling team, focusing on the development of the Accelerated Linear Algebra (XLA) TPU/GPU parallelizing compiler. This role is crucial for optimizing and scaling machine learning models across multiple accelerators for both internal and external customers.
The position involves working with cutting-edge technology in machine learning compilation, specifically on the XLA Single Program Multiple Data (SPMD) partitioner, collective and scheduling optimizations, and code generation. As part of Google Cloud, you'll be contributing to enterprise-grade solutions that leverage Google's advanced technology stack.
The ideal candidate should have a strong foundation in software development, data structures, and algorithms, with preferred experience in Machine Learning, High Performance Computing, and C++ programming. You'll be responsible for conducting performance analysis, implementing optimizations, and contributing to critical features that enhance production team efficiency.
This role offers the opportunity to work on projects that directly impact Google's core technologies and Cloud services, with the potential to influence how machine learning models are optimized and scaled across accelerator hardware. You'll be part of a team that serves customers in more than 200 countries, helping solve critical business problems through innovative technology solutions.
The position combines technical expertise with leadership opportunities, requiring both strong programming skills and the ability to collaborate with peers and stakeholders. You'll be at the forefront of developing solutions that enhance Google's machine learning infrastructure while working in an environment that values diversity, inclusion, and innovation.