Staff Software Engineer, Core Machine Learning, TPU, GPU

Google is seeking a Staff Software Engineer to join their Core Machine Learning team, focusing on TPU and GPU technologies. This role is at the forefront of machine learning inference, working to provide industry-leading solutions on both Tensor Processing Unit (TPU) and Graphics Processing Unit (GPU) platforms. The position involves creating seamless, efficient, and cost-effective inference experiences for users while building and optimizing third-party inference stacks.

The role requires deep expertise in machine learning frameworks, inference optimization, and cloud platforms. You'll be working with cutting-edge technology, contributing to open-source projects like virtual large language models (vLLM), and implementing TPU-specific backends. The position offers the opportunity to work on Google Cloud Platform's infrastructure and collaborate with cross-functional teams.

As a technical leader, you'll be responsible for managing project priorities, deadlines, and deliverables while contributing to technical roadmaps. The role combines hands-on development with strategic planning and team leadership. You'll be working in a dynamic environment where you can influence the future of machine learning infrastructure at Google.

The position offers competitive compensation including a base salary range of $197,000-$291,000, plus bonus, equity, and comprehensive benefits. This is an excellent opportunity for someone who wants to work at the intersection of machine learning, high-performance computing, and cloud infrastructure while making a significant impact on Google's machine learning capabilities.