Senior Software Engineer, Agentic Information Retrieval

Snapshot

We are seeking a talented Software Engineer to design, build, and refine autonomous systems that revolutionize how we access and process information. This role focuses on creating intelligent agents capable of understanding complex user queries, performing sophisticated information retrieval tasks, and ranking results for relevance and accuracy. You will be at the forefront of applying advanced AI to solve challenging search and data synthesis problems, directly contributing to the next generation of intelligent systems.

About Us

Artificial Intelligence could be one of humanity’s most useful inventions. At Google DeepMind, we’re a team of scientists, engineers, machine learning experts and more, working together to advance the state of the art in artificial intelligence. We use our technologies for widespread public benefit and scientific discovery, and collaborate with others on critical challenges, ensuring safety and ethics are the highest priority.

The Role

Join our team of engineers to shape the future of intelligent systems and information access. We are looking for motivated software engineers with a passion for building agentic applications that can reason, retrieve, and synthesize information. In this role, you will work on creating sophisticated agents that can navigate vast datasets, interact with various tools and APIs, and deliver precise, trustworthy answers to users. You’ll join an inspiring and collaborative environment, working on ground-breaking technology with potentially extraordinary impact.

Key responsibilities:

• Design, build, and maintain agentic applications focused on complex information retrieval and question-answering tasks.

• Develop and implement novel ranking algorithms to evaluate, filter, and prioritize information retrieved by AI agents.

• Integrate and fine-tune large language models (LLMs) to serve as the core reasoning engine for autonomous agents.

• Build robust data and evaluation pipelines to measure agent performance, track key metrics (e.g., accuracy, latency, relevance), and drive continuous improvement.

• Collaborate closely with research scientists and other engineering teams to translate cutting-edge ideas into production-ready systems.

• Engineer solutions for agent reliability, scalability, and efficiency to support a growing number of users and use cases.

About You

In order to set you up for success as a Software Engineer at Google DeepMind, we look for the following skills and experience:

• Proven experience in back-end software engineering using languages like Python or C++.

• Strong understanding of and experience with information retrieval, search, and/or question-answering systems.

• Experience designing and working with complex data pipelines and data analysis.

• Excellent interpersonal and communication skills for collaborating effectively with both technical and research-oriented colleagues.

• A bachelor's degree in Computer Science, a related technical field, or equivalent practical experience.

In addition, the following would be an advantage:

• Experience building applications using large language models (LLMs).

• Familiarity with building agentic systems or frameworks (e.g., involving planning, tool use, or reasoning).

• Basic understanding of statistics, data science, or machine learning evaluation techniques.

• Experience with modern vector search and indexing technologies.

At Google DeepMind, we value diversity of experience, knowledge, backgrounds and perspectives and harness these qualities to create extraordinary impact. We are committed to equal employment opportunity regardless of sex, race, religion or belief, ethnic or national origin, disability, age, citizenship, marital, domestic or civil partnership status, sexual orientation, gender identity, pregnancy, or related condition (including breastfeeding) or any other basis as protected by applicable law. If you have a disability or additional need that requires accommodation, please do not hesitate to let us know.