Staff Software Engineer, Agent Retrieval Search Platform

Google Cloud's software engineers develop the next-generation technologies that change how billions of users connect, explore, and interact with information and one another. 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 Cloud's needs with opportunities to switch teams and projects as you and our fast-paced business grow and evolve. You will anticipate our customer needs and be empowered to act like an owner, take action and innovate. 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. Agent Retrieval Search Platform journeys from data ingestion to search results evaluation. Its primary focus is on Developers at companies building applications that will need a high degree of adaptability over time, and the goal is to simple query serving journeys very easy to get started while providing adaptability that grows with customer requirements and complexity. To achieve the flexibility and visibility required, the platform introduces the concept of Components to simplify participation while providing a configurable serving layer to ensure observability is enabled by default. The Google Cloud AI Research team addresses AI challenges motivated by Google Cloud’s mission of bringing AI to tech, healthcare, finance, retail and many other industries. We work on a range of unique problems focused on research topics that maximize scientific and real-world impact, aiming to push the state-of-the-art in AI and share findings with the broader research community. We also collaborate with product teams to bring innovations to real-world impact that benefits our customers. Individual pay is determined by factors including job-related skills, experience, and relevant education or training. Poland: zł480000 - zł492000 (PLN) + 20% bonus target + equity + benefits Learn more about benefits at Google . Lead the technical execution and scoping of highly complex, ambiguous projects to systematically unblock core product limitations. You will turn open-ended scaling and performance issues into tractable, delivered systems. Drive the physical design and implementation decisions that ensure the backend system performs at scale. Build solutions that are flexible enough to offer internal tooling capabilities to consuming products, while reliably managing massive query volumes. Maintain a strong, direct presence by contributing to critical, code paths, authoring comprehensive technical designs, and performing code reviews. Identify and resolve performance bottlenecks in cost-performance, query latency, and throughput to keep latency curves flat as datasets grow. Minimum qualifications: Bachelor's degree or equivalent practical experience. 8 years of experience in software development. 5 years of experience building and developing infrastructure, distributed systems or networks, or experience with compute technologies, storage, or hardware architecture. 5 years of experience testing, and launching software products, and 3 years of experience with software design and architecture. Preferred qualifications: Experience designing, tuning, or building vector search systems (e.g., ANN approximate nearest neighbor indexing, vector embeddings management, hybrid lexical-vector searches, and co-located metadata storage). Experience architecting and deploying large-scale systems across any major Cloud platform. Expert-level knowledge of distributed systems—specifically data partitioning, replication, consistency models, and the trade-offs of building stateful versus serverless components. Strong background in backend systems engineering, including high-throughput data access layers, custom API design, concurrency controls, and persistent storage engines (e.g., Spanner, Key-Value stores).