Offensive Security Engineer: AI Security Prototyping

The Alan Turing Institute; Greater London; On-site; GBP 40,365 - 54,000; Full time

Benefits offered by this job

Flexible working

Family friendly policies

Employee-only benefits guide

Job summary

The Alan Turing Institute in London is seeking an Offensive Security Engineer to build and run the systems, tooling, and environments that turn research ideas into reliable, repeatable evidence for AI security research.

You will work with Offensive Security Researchers to stand up realistic test environments, develop reproducible implementations, and design experiments that assess AI-enabled cyber techniques in a safe, governed framework.

Responsibilities

• Develop prototypes, tools, infrastructure, and evaluation harnesses with Offensive Security Researchers and other Engineers.
• Stand up and maintain realistic test environments and ranges that allow offensive techniques to be run safely and meaningfully.
• Build and maintain reproducible implementations that support rigorous evaluation of AI-altered attack surfaces.

Job description

The Alan Turing Institute in London is seeking an Offensive Security Engineer to build and run the systems, tooling, and environments that turn research ideas into reliable, repeatable evidence for AI security research.

You will work with Offensive Security Researchers to stand up realistic test environments, develop reproducible implementations, and design experiments that assess AI-enabled cyber techniques in a safe, governed framework.