We are searching for a talented engineer passionate about bridging the gap between research and production for cutting-edge AI models. In this role, you'll play a key part in accelerating the hyperscale, low-latency deployment of Google DeepMind's Gemini models, across text, audio, image and video, and onto various product surfaces within Google. Your work will involve productionizing, optimizing and serving models, collaborating with research teams to ensure models are production-ready, and identifying ways to streamline the entire research-to-production process. This is a unique opportunity to directly impact the speed and efficiency with which Google delivers innovative AI-powered products and features to users.
About UsArtificial 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 RoleIn this role, you will be at the forefront of bringing cutting-edge AI research to life. You'll work directly with researchers and engineers to optimize and deploy multimodal large language models (LLMs) like Gemini onto Google's serving infrastructure, impacting users across a diverse range of applications and accelerating research projects. This involves a blend of technical expertise and collaborative problem-solving to ensure both efficiency and quality throughout the entire LLM development and deployment lifecycle.
Key responsibilities:- Bridge the infrastructure gap between research and production: Collaborate closely with research teams to understand next generation modeling approaches, ensuring they are designed and implemented with production considerations in mind.
- Optimize the serving environment: Contribute to and collaborate with other infrastructure teams to deliver serving infrastructure that is designed for maximum efficiency and performance, addressing bottlenecks in speed and scale.
- Design and implement novel, high-performance serving techniques: e.g., continuous batching, speculative decoding, request-level scheduling, for maximum throughput and efficiency.
- Streamline the deployment process: Identify opportunities to automate tasks, eliminate redundancies, and improve the overall velocity of model releases.
- Develop expertise in model serving technologies: Gain a deep understanding of serving frameworks, preprocessing pipelines, caching mechanisms, and other relevant technologies.
- Identify the best hardware setup for deploying a diverse set of models: Conduct deep performance profiling and improve efficiency of ML model serving on hardware accelerators.
- Stay informed on industry trends: Continuously learn about new technologies and best practices in the field of AI research and deployment.
This is a chance to make a real difference in the way Google develops and deploys AI, directly impacting the speed and effectiveness with which we deliver innovative solutions to users.
About YouIn order to set you up for success as a Software Engineer at Google DeepMind, we look for the following skills and experience:
- Interpersonal skills, such as discussing technical ideas effectively with colleagues and collaborating with other roles
- Excellent knowledge of either C++ or Python
- Experience with deployment in production environments
- Experience with developing serving infrastructure
- Familiarity or experience with optimisation of distributed ML systems
- Familiarity with modern HW accelerators (GPU / TPU)
Deadline - 12th December 2025
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.
