Staff Software Engineer, Agent Quality

Google•Sunnyvale, CA

9d•$207,000 - $300,000

About The Position

Google software engineers build technologies that help billions of users connect, explore, and interact with information. This role is part of Cloud Applied AI (AAI), which powers business growth with Gemini Enterprise. The portfolio includes Gemini Enterprise for Customer Experience and other vertical and domain packaged solutions. The team builds quickly deployable solutions and new capabilities with startup agility, works closely with model builders, and develops AI products in a fast-paced, collaborative environment. The Staff Software Engineer will focus on agent quality, building multimodal agents and systems that enable agents to be developed, tested, evaluated, and improved. The role includes embedding Gemini and Vertex AI intelligence into enterprise infrastructure and working with partner teams to shape foundational agent frameworks.

Requirements

Bachelor's degree or equivalent practical experience.
8 years of experience in software development.
5 years of experience testing and launching software products.
3 years of experience with software design and architecture.
5 years of experience leading ML design and optimizing end-to-end machine learning, such as model deployment, model evaluation, data processing, debugging, and fine-tuning.
2 years of experience with GenAI techniques, such as LLMs, multimodal systems, or large vision models, or with GenAI-related concepts such as language modeling or computer vision.
2 years of experience building Generative AI applications, agentic workflows, and GenAI quality evaluation.

Nice To Haves

Master’s degree or PhD in Engineering, Computer Science, or a related technical field.
8 years of experience with data structures and algorithms.
3 years of experience in a technical leadership role leading project teams and setting technical direction.
3 years of experience working in a complex, matrixed organization involving cross-functional or cross-business projects.

Responsibilities

Lead the definition and execution of engineering standards and no-regression release gates to ensure response accuracy, safety, and brand alignment.
Build core logic for multimodal agents that perform complex reasoning for business needs across areas such as sales, support, and finance.
Develop automated meta-layers that allow agents to iteratively build, test, and refine other agents.
Embed Gemini and Vertex AI intelligence into enterprise infrastructure and collaborate with partner teams, including Google DeepMind, to shape foundational agent frameworks.
Use data-driven analysis and evaluation pipelines to improve model performance, optimize prompts, and reduce hallucinations.