Senior Software Engineer, Earth AI, Research

Google•Mountain View, CA

About The Position

Google'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. EarthAI is a frontier initiative at Google Research to build the world’s most advanced planetary foundation models and bring it together with Gemini based reasoning to understand, plan, and act to help address some of the most critical challenges of our time. Our team develops models that interpret the world's physical dynamics—from global mobility and population shifts to environmental signals—transforming the entire planet into an interactive environment for understanding and reasoning. You will work closely with our research team to bridge the gap between cutting-edge research and scalable engineering to take Earth AI Agents from research to production. You will play a critical role in building production-grade agentic features, evaluation frameworks, data pipelines necessary to validate and deploy multimodal generative AI and agentic systems at a massive scale. Google Research addresses challenges that define the technology of today and tomorrow. From conducting fundamental research to influencing product development, our research teams have the opportunity to impact technology used by billions of people every day. Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field -- we publish regularly in academic journals, release projects as open source, and apply research to Google products.

Requirements

Bachelor’s degree or equivalent practical experience.
5 years of experience with software development in Python or C++.
Experience designing and implementing Generative AI Agents, including prompt engineering, multi-turn reasoning, and tool use.
Experience implementing core AI algorithms or concepts.
Experience designing and implementing software systems, including testing, code review, and debugging.

Nice To Haves

Master’s degree in Computer Science, Artificial Intelligence, or a related technical field.
Experience building and maintaining evaluation frameworks or data pipelines for machine learning models.
Experience working with geospatial data, satellite imagery, or large-scale environmental datasets.
Familiarity with Large Language Models (LLMs), generative AI, or multi-agent systems.

Responsibilities

Build and scale the infrastructure for advanced multi-agent systems, enabling Gemini-powered agents to perform complex, multi-step reasoning, planning, and execution tasks on a global scale.
Design, build, and maintain robust evaluation pipelines and metrics to rigorously assess the performance, reasoning capabilities, and reliability of planetary-scale multimodal models and integrate human generated groundtruth.
Partner directly with Research Scientists to accelerate innovation by prototyping new features, optimizing experimental loops, and implementing complex model architectures in code.
Develop and optimize the software infrastructure required for training, fine-tuning, and serving Gemini-based agents, ensuring high performance and reliability across multiple surfaces.
Translate research concepts into high-quality, reusable software components and APIs that allow our models to be deployed into real-world products and impact billions of lives.