Staff ML Compiler Engineer, TPU Performance Optimizations

Google Cloud's software engineers develop the next-generation technologies that change how billions of users connect, explore, and interact with information and one another. We're looking for engineers who bring fresh ideas from all areas, including information retrieval, distributed computing, large-scale system design, networking and data storage, security, artificial intelligence, natural language processing, UI design and mobile; the list goes on and is growing every day. As a software engineer, you will work on a specific project critical to Google Cloud's needs with opportunities to switch teams and projects as you and our fast-paced business grow and evolve. You will anticipate our customer needs and be empowered to act like an owner, take action and innovate. We need our engineers to be versatile, display leadership qualities and be enthusiastic to take on new problems across the full-stack as we continue to push technology forward.

Our team is focused around driving continuous improvements to the machine learning software/hardware stack and TPU compiler for Google first-party teams, and for Google Cloud Platform (GCP) customers.

In this role, you will build the infrastructure powering the world’s most advanced machine learning.You will drive the future of Tensor Processing Unit (TPU) performance. You will design and implement advanced compiler optimizations such as pipelining, prefetching, and fusions to maximize TPU efficiency. You will directly impact internal Alphabet initiatives, including Large Language Model (LLM) development and chip co-design, while empowering external cloud customers. You will collaborate across teams to integrate frameworks like PyTorch and ensure the hardware remains the industry’s premier Machine Learning (ML) platform.The Google Cloud AI Research team addresses AI challenges motivated by Google Cloud’s mission of bringing AI to tech, healthcare, finance, retail and many other industries. We work on a range of unique problems focused on research topics that maximize scientific and real-world impact, aiming to push the state-of-the-art in AI and share findings with the broader research community. We also collaborate with product teams to bring innovations to real-world impact that benefits our customers.

Responsibilities:

• Learn and build an intuitive understanding of various parts of Google’s ML stack: Frameworks (e.g., JAX, PyTorch), XLA and runtime stack.
• Research and develop the novel compiler optimizations targeting ML workloads, and emerging architectures.
• Identify opportunities to improve the efficiency of the ML workloads through insightful performance debugging for ML workloads and custom kernels, and build compiler solutions to deliver those improvements.
• Provide technical leadership and mentorship as a Team Lead (TL), and explore strategic initiatives.

Minimum qualifications:

• Bachelor's degree or equivalent practical experience.
• 8 years of experience in software development.
• 3 years of experience with software design and architecture.
• Experience with machine learning, compilers, computer architecture, GPU programming, C++, Python.

Preferred qualifications:

• Experience in open-source software development, including experience in releasing and supporting open-source projects.
• Experience with ML compilers and their internals, experience writing compiler optimization passes.
• Experience with debugging correctness and performance issues at all levels of the ML Software (SW) stack.
• Experience with GPU or TPU performance analysis.
• Comfortable with accelerator Hardware (HW) architectures (TPUs/Graphics Processing Unit (GPUs)).
• Comfortable debugging correctness and performance issues at all levels of the stack.