← All roles

Software Engineer III, Performance

Apply on company site
Mountain View, CA, USA$147k - $210kFull-timePosted 3d ago

About the role

Google Cloud performance-focused software engineering role working on OSS model optimization and agentic AI techniques to improve model performance and provide tooling for external customers.

Responsibilities

  • Write product or system development code. Manually optimize models, using state-of-the-art techniques (sharding, quantization, custom kernels).
  • Develop principles from manual optimizations which can be automated via agentic AI (e.g., compute, communication, scheduling, or quantization cost models).
  • Land identified principles and recipes to build scalable solutions, for example, by collaborating with the compiler team on cost modeling or by building agentic tooling for headroom analysis.
  • Create scalable solutions to serve the third-party customer base by improving out-of-the-box software performance and open-sourcing tooling to external customers.
  • Develop trend analysis to identify performance issues in yet-unseen models, solving performance problems before they occur. While maintaining model benchmarks to ensure tracking of performance wins.

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 computer architecture, performance analysis, and performance modeling.
  • Experience experimenting with AI agents or LLM-powered agentic workflows.
  • Experience in systems engineering.

Skills

Required:Software developmentComputer architectureAI agents / LLM-powered workflowsSystems engineering
Last updated Oct 23, 2026. Interested? Apply on the company site.

About Google

Google Search homepage

llmtext-to-speechvoice-ai-stack

More open roles at Google