Frontier AI Security Engineer

Swift Software; Greater London; On-site; GBP 120,000 - 180,000; Full time

Job summary

Swift is seeking an expert in AI security to run frontier AI models against its codebase, identify hidden vulnerabilities, and build scalable AI-assisted detection pipelines in a highly regulated fintech environment. You will design experiments, evaluate models, and integrate findings into secure software development practices.

The role requires deep security knowledge, strong programming skills, and the ability to communicate complex decisions clearly to security engineers.

Qualifications

• Demonstrated hands-on experience applying AI/LLM models to real security testing or vulnerability research.
• Strong software engineering ability: read, navigate, and reason about large codebases directly, across multiple languages.
• Deep working knowledge of application security fundamentals: vulnerability classes, exploit mechanics, and how analysis tools work.

Responsibilities

• Run frontier AI models directly against SWIFT's codebases to find vulnerabilities that conventional tools miss
• Build the methodology for this work through direct experimentation
• Build the pipeline that makes AI-assisted detection usable at scale: includes validation, deduplication, and routing to remediation
• Run head-to-head technical evaluations of frontier models on real detection tasks and base decisions on testing evidence
• Build the integration that plugs AI-assisted detection into how SWIFT develops software alongside existing security tooling
• Find vulnerability classes current tooling cannot see and build detection to catch them ahead of others

Skills

AI/LLM security

Codebase analysis

Security testing

Scripting/automation

Model evaluation

Technical communication

Ambiguity handling

Education

University degree in Computer Science or related field

Masters degree asset

Job description

Swift is seeking an expert in AI security to run frontier AI models against its codebase, identify hidden vulnerabilities, and build scalable AI-assisted detection pipelines in a highly regulated fintech environment. You will design experiments, evaluate models, and integrate findings into secure software development practices.

The role requires deep security knowledge, strong programming skills, and the ability to communicate complex decisions clearly to security engineers.