logo

AI Job Summary

Research and implement state-of-the-art algorithmic optimizations like quantization for AI models, validate them through customer projects, and transition them to production teams. Develop custom kernels in Pallas, collaborate on hardware-software co-design for TPU architecture, and analyze performance across large-scale systems. Requires a bachelor's degree, two years of software development experience, and two years working with performance analysis, computer architecture, and large-scale systems data.

Written from this posting by Neural Jobs AI. The full description is below.

AI Resume Tailoring Sign in to use this AI Cover Letter Sign in to use this

Job Description

  • Track the AI market, including the latest open-source models, frameworks, and research breakthroughs to identify SOTA algorithmic optimization opportunities.
  • Identify and validate SOTA algorithmic optimizations (e.g., quantization, mxfp4) through white-glove projects for key internal customers.
  • Drive end-to-end impact by transitioning validated algorithms and recipes to the Frontier Model Performance (manual optimization) and Automation teams, ensuring streamlined scaling.
  • Collaborate on hardware/software co-design to guide future TPU architecture (e.g., nvfp4) and product capabilities.
  • Develop custom kernels (Pallas) for new algorithmic efficiency techniques, and put them into production for 3P/OSS and 1P models.

Minimum qualifications:

  • Bachelor’s degree or equivalent practical experience.
  • 2 years of experience with software development in one or more programming languages.
  • 2 years of experience with performance, large-scale systems data analysis, visualization tools, or debugging.
  • 2 years of experience with computer architecture, performance analysis, and performance modeling.

Preferred qualifications:

  • Master's degree or PhD in Computer Science or related technical fields.
  • 2 years of experience with data structures and algorithms.
  • Experience with hardware-software algorithmic co-design and computer architecture analysis.
  • Experience developing accessible technologies.
  • Strong background in ML models and systems.
  • Bachelor’s degree or equivalent practical experience.
  • 2 years of experience with software development in one or more programming languages.
  • 2 years of experience with performance, large-scale systems data analysis, visualization tools, or debugging.
  • 2 years of experience with computer architecture, performance analysis, and performance modeling.
Do you match this job?

Here is what this employer asked for. Sign in and we will fill in your half.

  • Role Software Engineer III, Performance
  • Experience 3-4 years
  • Education Bachelor Degree, or equivalent experience
  • Work type On-site
  • Location United States
Check my match (free)
Google
AI Research Lab · 500+ Members · Mountain View, CA, United States

Google builds internet, software, cloud, and AI products used by consumers, developers, and organizations. Its portfolio includes Search, YouTube, Android, Chrome, Maps, Gmail, Workspace, Google Cloud, advertising platforms, devices, and Gemini AI products. The company develops large-scale computing infrastructure and research that power information retrieval, communication, productivity, media, navigation, and machine learning. Google is the largest operating business within Alphabet and earns a substantial share of its revenue from digital advertising.

91 more Software Engineer roles in Sunnyvale

Job Overview

Approx. salary range

152K – 266K

Our estimate — this employer did not publish a salary

Our estimate, not the employer’s. Worked out from the middle half of 148 comparable roles on Neural Jobs that did publish a salary, in the same field, country and experience band. The real figure for this job may be different.

Eligibility
United States Right to work in the United States required.
Workplace
On-site
Job Posted:
2 days ago
Job Type
Full Time
Education
Bachelor Degree, or equivalent experience
Experience
3-4 years

Share This Job: