Software Engineer, Gemini App Skills Platform, DeepMind

About the role

MINIMUM QUALIFICATIONS:

• Experience developing software with large language models, agentic workflows,

tool use, or retrieval-augmented generation (RAG).

• Experience designing evaluation datasets, automated rating systems, or

conducting error analysis and prompt optimization for generative models.

PREFERRED QUALIFICATIONS:

• Experience collaborating cross-functionally across research, product, and

platform engineering teams to take novel AI features from prototype to

production.

• Demonstrated ability to design experimental setups, analyze model telemetry,

and define reproducible metrics for complex features.

ABOUT THE JOB:

Join DeepMind’s mission to solve intelligence and benefit humanity by building

the next generation of agentic AI. As a Software Engineer on the Gemini App

Skills Platform, you will be a key contributor to the extensible execution layer

that transforms Gemini from a conversational assistant into an action-oriented,

universal agent.

In this role, you will architect the systems that allow Gemini to discover,

retrieve, and execute modular capabilities (skills) across Google, DeepMind, and

third-party ecosystems. Your work will bridge foundation model intelligence and

real-world execution spanning dynamic context engineering (system instructions),

low-latency routing algorithms, and automated evaluation frameworks. While this

role focuses heavily on Large Language Model (LLM) behavior and evaluation, you

will dive directly into Gemini app’s production serving infrastructure

(primarily C++) and Python evaluation pipelines to make high-impact, hands-on

architectural enhancements. You will have an opportunity to operate at the

center of Google’s flagship AI product. You will see your code, prompts, and

evaluation standards actively shape the user experience for hundreds of millions

of users across web, mobile (Android/iOS), and Chrome, helping define how people

and AI interact with software.

Artificial intelligence will be one of humanity’s most transformative

inventions. At DeepMind, we are a pioneering AI lab with exceptional

interdisciplinary teams focused on advancing AI development to solve complex

global challenges and accelerate high-quality product innovation for billions of

users. We use our technologies for widespread public benefit and scientific

discovery, ensuring safety and ethics are always our highest priority.

We are pushing the boundaries across multiple domains. Our global teams offer

diverse learning opportunities and varied career pathways for those driven to

achieve exceptional results through collective effort.

Individual pay is determined by factors including job-related skills,

experience, and relevant education or training.

US: $174000 - $252000 (USD) + 15% bonus target + equity + benefits

Learn more about benefits at Google

[https://www.google.com/about/careers/applications/benefits/].

RESPONSIBILITIES:

• Design and build intelligent skill discovery, hybrid routing architectures,

and low-latency C++ serving components across Gemini on web, mobile, and

Chrome.

• Pioneer dynamic system instructions, prompt representations, and semantic

retrieval schemas that enable Gemini to seamlessly navigate expanding skill

catalogs without attention dilution or quality regressions.

• Design automated evaluation frameworks (auto-raters, simulated environments,

and benchmarking suites) to rigorously measure single-turn triggering

precision, multi-turn tool, and parameter validity.

• Perform in-depth loss analysis on production telemetry, drive iterative

prompt/model hill-climbing to surpass quality thresholds, and set standards

for system reliability and clean architecture across the organization.

• Partner closely with DeepMind Research, Search, Vertical teams (e.g., local,

shopping), and external Engineering teams to onboard new modular capabilities

onto the platform.