Research Scientist, AI Security & Vulnerability

DeepMind Technologies Limited; Mountain View (CA); On-site; USD 174,000 - 252,000; Full time

Benefits offered by this job

Equity

Bonus target

Benefits

Job summary

Google DeepMind is seeking a Research Scientist to set up large-scale tests and deploy ideas quickly, applying the latest theories to develop new products and technologies. You will work on AI safety, security, and ML-powered tooling, contributing to both research and production pipelines.

The role involves creating experiments, prototyping architectures, and collaborating across teams to land transformative impact for Google DeepMind and its cybersecurity initiatives.

Qualifications

• PhD degree in Computer Science or Computer Engineering, or equivalent practical experience.
• Experience with vulnerability research (auditing, reverse engineering, exploitation).
• Experience building infrastructure, developer tools, or ML-based applications.
• Publication record in AI conferences (NeurIPS, CVPR, ICCV, ICLR).

Responsibilities

• Learn and apply the latest theories to develop new and improved products, processes, or technologies.
• Set up large-scale tests and deploy promising ideas quickly and broadly.
• Design, implement, and maintain scalable software infrastructure for CodeMender’s vulnerability detection and remediation services.
• Build evaluation pipelines, benchmarks, and leaderboards to measure agent performance.
• Collaborate with product and platform teams to deploy research-based solutions into Google's developer tools and workflows.

Skills

Vulnerability research

Infrastructure / developer tools

ML-based applications

Education

PhD in Computer Science or Computer Engineering

Bachelor's or Master's in Computer Science

Tools

Python

C++

Go

Job description

Google DeepMind is seeking a Research Scientist to set up large-scale tests and deploy ideas quickly, applying the latest theories to develop new products and technologies. You will work on AI safety, security, and ML-powered tooling, contributing to both research and production pipelines.

The role involves creating experiments, prototyping architectures, and collaborating across teams to land transformative impact for Google DeepMind and its cybersecurity initiatives.