Senior
Serving infrastructure for Gemini models at Google DeepMind
Join Google DeepMind's team building and scaling serving infrastructure for Gemini models in New York, including large-scale streaming and audio orchestration capabilities. This role requires production ML infrastructure experience — productionizing large language and multimodal models, not just training or research prototyping — plus C++ systems chops and the ability to drive technical direction for a team. Suited for senior engineers who've shipped ML systems at real production scale.
Step into this interview
Free · a live voice mock calibrated to this exact role
Likely format
Google's standard onsite loop typically includes coding, system design/ML infra design, and Googleyness/leadership behavioral rounds.
What this interview tests
- Productionizing LLMs/multimodal models (serving, deployment, evaluation)
- C++ for performance-critical systems
- Algorithm/data-structure choices for scalability
- Root-cause analysis and production debugging of ML systems
- Software architecture for reliability and performance
- Driving technical direction and team roadmap
Common question themes
Design a serving system for a large multimodal model with diverse client configurations
Describe debugging a production quality or latency regression in an ML system
How do you choose data structures/algorithms when scaling a system
Tell me about a technical direction or architecture decision you drove for your team
How would you build monitoring to catch model quality issues in production
Explain a large-scale streaming or real-time infrastructure challenge you've solved
Related interviews
Senior
Software Engineer, Serverless Networking, Infrastructure
Staff
Staff Software Engineer, Mobile (Android), YouTube
Associate
Software Engineer
Roblox
Senior
Senior Software Engineer, App Performance
Roblox
Senior
Senior Software Engineer, Game Engine Systems
Amazon
Mid