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.

Practice this interview

Free · a live voice mock calibrated to this exact role

Start the mock interview

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

How candidates describe it

Real Senior Software Engineer interview stories — retold from candidates' public write-ups, with sources.

Bloomberg · Senior Software EngineerOffer

Bloomberg Senior Software Engineer Interview: Five Rounds, Offer

A Senior Software Engineer candidate applied to Bloomberg's London office through the company's careers site and, after an initial screen, went through five separate on-site conversations covering coding, system design, a recruiter chat, and a hiring-manager round, ultimately accepting an offer.

Interviewed October 2022 · London, United Kingdom

Google · L3 Software EngineerOffer

Google L3 software engineer interview: phone screen, four coding rounds, and the Googleyness round

A candidate with two years of experience went from recruiter outreach to offer over about four months. The onsite was four 45-minute coding rounds — three of them featuring binary trees — and one round turned into a 25-minute chain of follow-ups about approximating an optimal solution at scale.

Interviewed June 2020 · Bangalore, IN

Google · L4 Software EngineerNo offer

Google L4 Software Engineer Interview: Eight Rounds, No Offer

An L4 Software Engineer candidate went through two phone screens, three onsite rounds, a culture conversation, and a team-matching call with a Google hiring manager, then watched the process stall for about a month and a half over a tightened experience requirement before an added extended round ended without an offer.

Interviewed February 2024 · Not specified

View the original posting

All Google Senior Software Engineer interviews

All Google interviews