info_outline
X In most instances, this position requires in-person interviews as part of the hiring process.
Minimum qualifications: - 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 (e.g., model deployment, model evaluation, data processing, debugging).
- Experience designing, building, or deploying Generative AI agents using Large Language Models (LLMs).
Preferred qualifications: - Master's degree or PhD in Computer Science or 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 .
About the jobWe are one of the teams building the Gemini agent, the agent harness for Google Workspace (Gmail, Docs, Drive, Sheets, Slides, Calendar, Chat) and Gemini Enterprise. We own parts of the Go harness, along with the benchmarks and evaluation pipelines used to measure and improve agent quality and latency.
Our team focuses on the efficiency of the agent: long context and agent tooling, especially Workspace search. Deciding what goes into the model's context window at each step is key to making agents efficient, and it is still an open problem.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
US: $174000 - $252000 (USD) 15% bonus target equity benefits
Learn more about benefits at Google .
Responsibilities - Design how the agent searches Workspace and what stays in the model's context window across turns, and measure the effect on quality and latency.
- Build and improve core parts of the Gemini agent harness in Go, including tool and Command-Line Interface (CLI) execution, citations, latency, and reliability.
- Debug evaluation and production traces to find root causes and fix them in the Go harness, tool, skill, or a prompt.
- Lead projects end-to-end, including work with partner teams across Workspace, Cloud AI and Gemini.
- Build evaluation infrastructure, datasets, and automated scorers so benchmark runs are fast and the results can be trusted.