Apply on Employer Site

Google DeepMind · 4 days ago

Research Engineer, Agentic Safety

United States

Full-time

Remote

Mid Level

Google DeepMind is a dedicated scientific community committed to solving intelligence and ensuring technology is used for public benefit. The Research Engineer will collaborate with experts to build technologies that enhance the safety of AI agents, addressing critical challenges in reliability and trustworthiness.

Artificial Intelligence (AI)Business DevelopmentFoundational AIMachine Learning

Growth Opportunities

Responsibilities

Develop frameworks to evaluate the safety, security and privacy of agentic AI systems at scale across key usecases at Google and GDM

Work on agent orchestration prototypes combining multiple AI components to reliably solve complex tasks in nuanced scenarios

Build leaderboards and evaluation metrics for the project to hill-climb

Integrate novel agentic technologies into research prototypes

Work with product teams to gather research requirements and consult on the deployment of research-based solutions to help deliver value incrementally

Amplify the impact by generalizing solutions into reusable libraries and frameworks for privacy preserving AI agents across Google, and by sharing knowledge through design docs, open source, or external blog posts

Qualification

PythonMachine LearningSoftware EngineeringQuantitative SkillsPassion for AIScripting LanguagesPipelining ToolsCreative Problem Solving

Required

Bachelor in computer science, security or related field, or equivalent practical experience

Passion for accelerating the development of secure agents using innovative technologies

Strong programming experience

Demonstrated record of python implementations of LLM pipelines

Quantitative skills in maths and statistics

Experience with common scripting languages and pipelining tools

Preferred

Experience in applying machine learning techniques to problems surrounding scalable, robust and trustworthy deployments of models

Experience with GenAI language models, programming languages, compilers, formal methods, and/or private storage solutions

Demonstrated success in creative problem solving for scalable teams and systems

A real passion for AI!

Company

Google DeepMind

Glassdoor4.5

Google DeepMind aims to research and build safe artificial intelligence system to solve intelligence and advance science and humanity. It is a sub-organization of Google.

Founded in 2010