Staff Software Engineer: Performance & Kernel

Google DeepMind; San Francisco (CA); On-site; USD 207,000 - 300,000; Full time

Job summary

Google DeepMind is seeking a Software Engineer to develop performance software for next-generation systolic array accelerators. The role involves identifying leveraged algorithms, building productivity tooling, and collaborating with ML and hardware teams to optimize performance and programmability.

The position emphasizes tackling challenging problems across AI research and production environments, with a strong foundation in software engineering and interest in accelerator-focused development.

Qualifications

• Bachelor’s degree or equivalent practical experience.
• 8 years of experience in software development.
• 5 years of experience testing, and launching software products.
• 5 years of experience in power or performance modeling or system performance analysis.
• 5 years of experience with Linux Kernel development and software and hardware architecture.
• 3 years of experience with software design and architecture.

Responsibilities

• Write low-level performance software for a new systolic array accelerators.
• Identify high-value algorithms and problems that are a match to this new machines.
• Use that direct experience delivering production code to build programming infrastructure to ease programming on the new accelerator for the performance software engineers and general software engineers who follow.
• Collaborate with application, algorithm, and performance-tuning experts to codesign solutions for the best efficiency, performance, and programmability.
• Communicate the performance, programmability, and efficiency results to our team and to our partner teams.

Skills

Linux kernel development

Performance modeling

System performance analysis

Software development

Software testing

Education

Bachelor's degree or equivalent practical experience

Master’s degree or PhD in Engineering/CS

Job description

Google DeepMind is seeking a Software Engineer to develop performance software for next-generation systolic array accelerators. The role involves identifying leveraged algorithms, building productivity tooling, and collaborating with ML and hardware teams to optimize performance and programmability.

The position emphasizes tackling challenging problems across AI research and production environments, with a strong foundation in software engineering and interest in accelerator-focused development.