Google

About Google

Empowering the world through technology and information

🏒 TechπŸ‘₯ 100K+πŸ“… Founded 1998πŸ“ Mountain View, California, United States

Key Highlights

  • Over 100,000 employees globally
  • Headquartered in Mountain View, California
  • Parent company Alphabet Inc. valued at $1.5 trillion
  • Google Cloud Platform serves millions of customers

Google LLC, headquartered in Mountain View, California, is a global leader in internet-related services and products, including its flagship search engine, Google Search, and the Android operating system. With over 100,000 employees, Google also offers cloud computing services through Google Cloud P...

🎁 Benefits

Google offers competitive salaries, equity options, generous PTO policies, comprehensive health benefits, and a remote work policy that allows flexibi...

🌟 Culture

Google is known for its engineering-first culture, emphasizing innovation and collaboration. The company fosters a unique environment that encourages ...

Google

Staff Engineer β€’ Senior

Google β€’ Mountain View - On-Site

Posted 1w agoπŸ›οΈ On-SiteSeniorStaff EngineerπŸ“ Mountain ViewπŸ’° $197,000 - $291,000 / yearly
Apply Now β†’

Overview

Google is hiring a Staff Software Engineer for TPU Performance to enhance machine learning infrastructure and optimize performance on TPU hardware. You'll work with technologies like CUDA and TensorFlow, requiring 8+ years of experience.

Job Description

Who you are

You have a Bachelor's degree or equivalent practical experience, along with 8 years of experience in software development. Your background includes 5 years of experience testing and launching software products, and 3 years of experience with software design and architecture. You possess deep expertise in machine learning, particularly in areas such as speech/audio technology, reinforcement learning, and ML infrastructure. Your experience also includes 5 years with ML design and infrastructure, focusing on model deployment, evaluation, data processing, debugging, and fine-tuning.

You hold a Master’s degree or PhD in Engineering, Computer Science, or a related technical field, and have 8 years of experience with data structures and algorithms. Your familiarity with machine learning, compiler optimization, code generation, and runtime systems for GPU architectures (such as OpenXLA, MLIR, Triton) sets you apart. You have a strong understanding of how to tailor algorithms and ML models to exploit the strengths of ML accelerator architectures while minimizing their weaknesses. Additionally, you are skilled in low-level GPU programming (CUDA, OpenCL) and performance tuning techniques, with a solid grasp of modern GPU, TPU, or other ML accelerator architectures, memory hierarchies, and performance bottlenecks.

What you'll do

In this role, you will engage with Google product teams and researchers to solve performance problems, such as onboarding new ML models and products on Google’s TPU hardware. You will enable larger models to train efficiently on a very large scale, utilizing thousands of TPUs. Your responsibilities will include analyzing performance and efficiency metrics to identify bottlenecks, and designing and implementing solutions that operate at Google fleet-wide scale. You will collaborate closely with cross-functional teams to ensure that the software you develop meets the high standards required for performance and scalability.

What we offer

At Google, you will be part of a team that develops next-generation technologies that change how billions of users connect, explore, and interact with information. You will have the opportunity to work on products that handle information at massive scale, extending well beyond web search. We encourage you to apply even if your experience doesn't match every requirement, as we value diverse perspectives and backgrounds. Join us to make a significant impact in the field of machine learning and software engineering.

Interested in this role?

Apply now or save it for later. Get alerts for similar jobs at Google.