Staff Software Engineer, ML Performance, GPUs
Description For Staff Software Engineer, ML Performance, GPUs
Google is seeking a Staff Software Engineer specialized in Machine Learning Performance and GPUs to join their team. This role is crucial for optimizing the performance of Google's cutting-edge Large Language Models (LLMs) including Gemini, Search, and Cloud LLM applications.
The position offers an exciting opportunity to work at the intersection of machine learning and hardware optimization, focusing on making Google's ML infrastructure more efficient and powerful. You'll be responsible for analyzing and improving the performance of LLM systems, working with GPU architecture, and driving optimization efforts across multiple teams.
As a Staff Software Engineer, you'll be part of Google's broader mission to develop next-generation technologies that impact billions of users worldwide. The role requires deep expertise in both software engineering and machine learning, with a particular focus on performance optimization and GPU programming.
The ideal candidate will have extensive experience in software development, ML infrastructure optimization, and performance analysis. You'll work closely with various product teams to solve complex ML model performance challenges and help scale LLM training across thousands of GPUs.
Google offers a competitive compensation package, including a base salary range of $189,000-$284,000, plus bonus, equity, and comprehensive benefits. The company is known for its innovative culture, commitment to diversity and inclusion, and opportunities for professional growth and impact.
This role is perfect for someone who is passionate about pushing the boundaries of ML performance, has strong technical leadership skills, and wants to work on problems that affect the future of AI technology. You'll be working with some of the most advanced ML systems in the world while collaborating with talented engineers across Google's organizations.
The position is based in Mountain View, CA, where you'll have access to Google's state-of-the-art facilities and resources. As part of Google Cloud, you'll be contributing to a platform that serves customers in more than 200 countries and territories, helping organizations digitally transform their businesses through cutting-edge technology.
Responsibilities For Staff Software Engineer, ML Performance, GPUs
- Analyze Large Language Model (LLM) performance and optimizations for partner teams including Google Gemini, Search, Cloud LLM and APIs
- Identify and maintain LLM training and serving benchmarks
- Drive XLA:GPU/Triton performance and guide future XLA releases
- Engage with Google product teams to solve ML model performance challenges
- Enable LLMs to train efficiently on a very large scale
- Run architecture-level simulations on GPU designs and perform roofline analysis
- Analyze performance and efficiency metrics to identify bottlenecks, design, and implement solutions
Requirements For Staff Software Engineer, ML Performance, GPUs
- Bachelor's degree or equivalent practical experience
- 8 years of experience in software development, and with data structures/algorithms
- 5 years of experience testing, and launching software products
- 3 years of experience with software design and architecture
- 5 years of experience leading ML design and optimizing ML infrastructure
- Experience with performance analysis and GPU programming
- Experience with machine learning systems
- Experience working on compiler optimizations
- Experience with architecture analysis and optimization
Benefits For Staff Software Engineer, ML Performance, GPUs
- bonus
- equity
- benefits package
Jobs Related To Google Staff Software Engineer, ML Performance, GPUs
