Join Google's innovative team and shape the future of how billions connect with information. As a Senior Software Engineer on the Search Platforms LLM Evaluation Infrastructure team, you will play a critical role in developing cutting-edge platforms that power advanced LLM evaluations for Google Search. This is an opportunity to work on massive-scale systems and contribute to a product used by people worldwide. We seek versatile engineers with a passion for tackling complex challenges across the full technology stack.

Our mission at Google is to organize the world's information and make it universally accessible. The Search LLM Evaluation Infrastructure team is building the next generation of core infrastructure and benchmarking platforms. These tools are essential for robust, automated, and scalable LLM evaluations across Google Search, ensuring quality, accuracy, and safety.

In this role, you will lead the architecture, design, and implementation of sophisticated LLM evaluation platforms and continuous benchmarking pipelines. Your work will transform complex evaluation workflows into a unified, high-throughput system capable of assessing advanced model architectures for quality, factual accuracy, safety, and latency. You will be instrumental in creating and evolving scalable, reproducible back-end infrastructure for systems operating at a global scale.

Architect, build, and maintain high-throughput, low-latency platform services and orchestration pipelines to execute automated evaluations, benchmark suites, and metric computations for Generative AI (GenAI) Search experiences.

Design robust evaluation systems that detect metric drift, optimize evaluation throughput, and scale model-assisted rating workflows while ensuring compute efficiency.

Drive the modernization and consolidation of fragmented, bespoke evaluation pipelines into a unified core platform, identifying capability gaps and creating reusable, extensible frameworks.

Optimize system throughput, execution turnaround times, and resource efficiency for continuous, high-volume evaluation workloads supporting production-critical Search models.

Integrate modern AI tooling, automated validation harnesses, and AI-assisted workflows into daily engineering practices to enhance developer velocity, evaluation excellence, and system robustness.

A Bachelor's degree or equivalent practical experience is required.

Demonstrate at least 5 years of experience in software development using one or more programming languages.

Possess 3 years of experience working with embedded operating systems and 3 years of experience testing, maintaining, or launching software products.

Have 1 year of experience in software design and architecture.

Preferred qualifications include a Master's degree or PhD in Computer Science or a related technical field, 5 years of experience with data structures and algorithms, and 1 year of experience in a technical leadership role. Experience developing accessible technologies is also valued.