Join Google Search AI and work at the intersection of industry leading
global scale. We apply breakthrough research, leveraging models like Gemini, to launch high-impact products that help billions ask any question and get things done. If you want to drive the future of AI in Search and work with world-class experts to deliver tangible, global impact and continuous innovation, this is the place.
Responsibilities
- Make models fast and cheap by picking speculative decoding, prefix caching, sharding, and quantization bets, proving them with load tests and live experiments, and landing them.
- Get to know every new Gemini revision better than its release notes do, analyze what changed in its architecture, behaviour, and cost to turn that into a serving topology that gets the most quality out of every TPU chip.
- Build the guardrails that let us move fast without breaking Search: configure checks, pre-submits, monitor and fast rollback, fix the root cause, not just the alert.
- Qualify new checkpoints, shape evaluation and autorater strategy, and explain why the new revision is suddenly slower, and what steps needs to be taken to improve it.
- Write the design documentation people read, and raise the bar in design and code reviews.
Minimum qualifications:
- Bachelor’s degree or equivalent practical experience.
- 5 years of experience with software development in one or more programming languages.
- 3 years of experience with full stack development, across back-end such as Java, Python, Golang, or C++ codebases, and front-end experience including JavaScript or TypeScript, HTML, CSS or equivalent.
- Experience designing, building, and operating large-scale distributed systems, with a focus on scalability, fault tolerance, and reliability.
- Experience with AI, Generative AI, data processing technologies, performance, or scalability optimizations.
- Experience working with data structures or Machine Learning algorithms.
Preferred qualifications:
- Master's degree or PhD in Computer Science or a related technical field.
- 3 years of experience with machine learning model serving, LLM inference, or machine learning evaluation systems.
- Experience optimizing performance or efficiency on hardware accelerators (TPUs or GPUs) through profiling, sharding, batching, caching, or quantization.
- Experience leading technical projects across teams from design through launch.
- Experience with distributed systems and safe production rollout practices.
- Ability to communicate with researchers, product teams, and leadership to make decisions.