Accelerator Software Engineer: HW/SW Co-Design

Google DeepMind; Mountain View (CA); On-site; USD 174,000 - 252,000; Full time

Benefits offered by this job

Bonus target 15%

Equity

Benefits

Job summary

Google DeepMind is seeking a highly skilled engineer to help build a next-generation AI compute platform in Mountain View and San Francisco. You will work on software-hardware codesign, ML acceleration, and high-performance inference workloads across cutting-edge systems.

The role requires a CS degree, strong Python and C++ experience, and the ability to operate in ambiguous environments. Compensation reflects skills, experience, and education, with equity and comprehensive benefits.

Qualifications

• Bachelor's degree in CS or related field, or equivalent practical experience.
• Experience with Python and C++ in software development.
• Experience with ML hardware accelerators and ML inference software.

Responsibilities

• Collaborate with product teams to design, implement, and prototype novel software algorithms.
• Oversee software/hardware codesign, kernel optimization, performance benchmarking and optimization.
• Collect insights to influence future software and hardware design and the technology roadmap.

Skills

Python

C++

ML accelerators

ML inference

Education

Bachelor's degree in Computer Science

Tools

Hardware accelerators

Job description

Google DeepMind is seeking a highly skilled engineer to help build a next-generation AI compute platform in Mountain View and San Francisco. You will work on software-hardware codesign, ML acceleration, and high-performance inference workloads across cutting-edge systems.

The role requires a CS degree, strong Python and C++ experience, and the ability to operate in ambiguous environments. Compensation reflects skills, experience, and education, with equity and comprehensive benefits.