Description

Minimum qualifications:

• Bachelor's degree or equivalent practical experience.
• 5 years of experience in software development.
• 3 years of experience with one or more of the following ML application: NLP, computer vision, Speech/audio, specialization in another ML field.
• 3 years of experience leading ML productionization or infrastructure optimization (e.g., model deployment, model evaluation, data processing, debugging, fine tuning).
• 1 year of experience in building Generative AI or agentic applications.

Preferred qualifications:

• Master's degree or PhD in Machine Learning or related field.
  
• 1 year in technical leadership role.
• Experience with core Generative AI modeling, leading Generative AI model productionization or infrastructure optimization.

About the jobGoogle's software engineers develop the next-generation technologies that change how billions of users connect, explore, and interact with information and one another. Our products need to handle information at massive scale, and extend well beyond web search. We're looking for engineers who bring fresh ideas from all areas, including information retrieval, distributed computing, large-scale system design, networking and data storage, security, artificial intelligence, natural language processing, UI design and mobile; the list goes on and is growing every day. As a software engineer, you will work on a specific project critical to Google's needs with opportunities to switch teams and projects as you and our fast-paced business grow and evolve. We need our engineers to be versatile, display leadership qualities and be enthusiastic to take on new problems across the full-stack as we continue to push technology forward.

As an engineer for these initiatives, you will transform the development of AI agents from an artisanal craft into an engineering discipline to achieve high-quality, reliability with multi-folds efficiency gains across Google. You will architect and productionize horizontal infrastructure, including generalized Knowledge Store libraries and self-reflection modules, to enable agents to learn and improve autonomously with every run. You will apply core design principles, lead deep audits of high-impact agents to extract deterministic logic from monolithic prompts into efficient, code-based workflows. You will scale automated prompt optimization and trace scanning tools to systematically eliminate waste and solve the "GenAI engineering gap" for teams building production-ready agents. Your work will bridge the gap between experimental prototypes and scalable production infrastructure, ensuring the entire agent ecosystem benefits from encoded best practices and high-performance solutions .Google Cloud accelerates every organization's ability to digitally transform its business and industry. We deliver enterprise-grade solutions that leverage Google's technology, and tools that help developers build more sustainably. Customers in more than 200 countries and territories turn to Google Cloud as their trusted partner to enable growth and solve their most critical business problems.

The US base salary range for this full-time position is $174,000-$252,000 bonus equity benefits. Our salary ranges are determined by role, level, and location. Within the range, individual pay is determined by work location and additional factors, including job-related skills, experience, and relevant education or training. Your recruiter can share more about the specific salary range for your preferred location during the hiring process.

Please note that the compensation details listed in US role postings reflect the base salary only, and do not include bonus, equity, or benefits. Learn more about benefits at Google.

Responsibilities

• Generalize horizontal tools, including a plug-in Knowledge Store and a Self-Reflection module, into reusable services that any agent can adopt to enable automated learning and improvement.
• Apply validated design principles to transition deterministic logic from monolithic prompts into efficient, code-based workflows that maximize reasoning value and ensure precise context control.
• Conduct deep architectural reviews and automated trace scanning for high-impact agents to eliminate structural inefficiencies and redundant tool calls in multi-turn reasoning chains.
• Extend automated prompt optimization frameworks to support multi-step workflows, enabling systematic improvement of both efficiency and quality across the agent ecosystem.
• Implement code-level safety enforcements and structured tool return patterns within the agent platform to ensure reliability and correctness on deterministic subtasks.

${qualifications}${responsibilities}
Requisition #: 78319205337703110

pca3lyuhf