Performance SOC Architect for ML Hardware

Google

Sunnyvale (CA)

On-site

USD 174,000 - 252,000

Full time

8 days ago
Application generator

Don’t send a generic resume — generate a resume and cover letter tailored to this exact role.

Get past ATS filters

Job summary

Google's software engineers develop the next-generation technologies that change how billions of users connect, explore, and interact with information. This role focuses on machine learning software/hardware stacks, providing insightful performance debugging for workloads and custom kernels.

You will summarize trace timelines, memory usage, and compiler profiles to drive improvements. Individual pay is determined by factors including job-related skills, experience, and relevant education or

Qualifications

  • Bachelor’s degree or equivalent practical experience.
  • 5 years of software development experience in one or more languages.
  • 3 years in performance, large-scale systems data analysis, or debugging.
  • 3 years in Computer Architecture, C++, Python, CUDA, GPU programming, or related technologies.
  • 3 years in testing/maintaining/launching software products with 1 year in design/architecture.

Responsibilities

  • Write and test product or system development code.
  • Learn data collection, analysis, and visualization workflows.
  • Support ML paradigms with end-to-end stack contributions.
  • Collaborate with Product Area leads to understand model optimization use cases, and hardware profiling requirements.
  • Collaborate across Hardware, Driver, Runtime, and Performance Analysis teams.

Skills

Software development
Performance analysis
Data visualization
Debugging
C++
Python
CUDA
GPU programming
GPU drivers
SoC
ASIC
Software testing
Software architecture

Education

Bachelor’s degree or equivalent practical experience
Master’s degree or PhD in Computer Science or related field

Job description

Google's software engineers develop the next-generation technologies that change how billions of users connect, explore, and interact with information. This role focuses on machine learning software/hardware stacks, providing insightful performance debugging for workloads and custom kernels.

You will summarize trace timelines, memory usage, and compiler profiles to drive improvements. Individual pay is determined by factors including job-related skills, experience, and relevant education or

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Performance SOC Architect - GPU/ML Profiling & Optimization
Performance SOC Architect - GPU/ML Profiling & Optimization

Google LLC • Sunnyvale (CA)

On-site
USD 174,000 - 252,000
Senior Software Engineer, Performance, SOC Architect
Senior Software Engineer, Performance, SOC Architect

Google • Sunnyvale (CA)

On-site
USD 174,000 - 252,000
Senior Software Engineer, Performance, SOC Architect
Senior Software Engineer, Performance, SOC Architect

Google LLC • Sunnyvale (CA)

On-site
USD 174,000 - 252,000
Staff Software Engineer, ML Systems Co-Design
Staff Software Engineer, ML Systems Co-Design

Google • Mountain View (CA)

On-site
USD 207,000 - 300,000
Engineering Manager, ML Performance
Engineering Manager, ML Performance

Google • Sunnyvale (CA)

On-site
USD 207,000 - 300,000
Senior Staff Performance Codesign Engineer, TPU
Senior Staff Performance Codesign Engineer, TPU

Google LLC • Sunnyvale (CA)

On-site
USD 240,000 - 333,000
Staff ML Systems Engineer - GPU & Performance
Staff ML Systems Engineer - GPU & Performance

Google • Sunnyvale (CA)

On-site
USD 207,000 - 300,000
Equity
Performance bonus
Machine Learning Hardware Architect, Google Cloud
Machine Learning Hardware Architect, Google Cloud

Google Inc. • Sunnyvale (CA)

On-site
USD 163,000 - 236,000
Engineering Manager, ML Performance
Engineering Manager, ML Performance

Google LLC • Sunnyvale (CA)

On-site
USD 207,000 - 300,000
Staff Software Engineer - TPU Performance & ML Infra
Staff Software Engineer - TPU Performance & ML Infra

Google • Ionia (NY)

On-site
USD 207,000 - 300,000