Senior Software Engineer, AI/ML, Workspace Intelligence

Google•Sunnyvale, CA
•$174,000 - $252,000

About The Position

Google Cloud software engineers develop technologies that help users connect, explore, and interact with information. This role works on the Gemini agent harness for Google Workspace—including Gmail, Docs, Drive, Sheets, Slides, Calendar, and Chat—and Gemini Enterprise. The team owns parts of the Go harness as well as benchmarks and evaluation pipelines used to measure and improve agent quality and latency. The team focuses on agent efficiency, including long context, agent tooling, and Workspace search. The role helps determine what information enters the model’s context window at each step, an open problem central to making agents efficient. The engineer will work on projects important to Google Cloud, anticipate customer needs, take ownership, innovate, and address problems across the full stack.

Requirements

  • Bachelor’s degree or equivalent practical experience.
  • 5 years of experience with software development in one or more programming languages.
  • 3 years of experience testing, maintaining, or launching software products, and 1 year of experience with software design and architecture.
  • 3 years of experience with end-to-end machine learning, such as model deployment, model evaluation, data processing, and debugging.
  • Experience designing, building, or deploying Generative AI agents using Large Language Models (LLMs).

Nice To Haves

  • Master’s degree or PhD in Computer Science or a related technical field.
  • 5 years of experience with data structures and algorithms.
  • 1 year of experience in a technical leadership role.
  • Experience programming in Go, Python, or C++.

Responsibilities

  • Design how the agent searches Workspace and what remains in the model’s context window across turns, and measure the effects on quality and latency.
  • Build and improve core parts of the Gemini agent harness in Go, including tool and CLI execution, citations, latency, and reliability.
  • Debug evaluation and production traces to identify root causes and fix issues in the Go harness, a tool, a skill, or a prompt.
  • Lead projects end to end, including collaboration with partner teams across Workspace, Cloud AI, and Gemini.
  • Build evaluation infrastructure, datasets, and automated scorers so benchmark runs are fast and results are trustworthy.

Benefits

  • 15% bonus target
  • Equity
  • Benefits
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service