In this role you will apply frontier AI models to SWIFT’s codebase to uncover vulnerabilities beyond traditional tools. You’ll design experiments, build scalable AI-assisted detection pipelines, and evaluate models to guide secure software development. You’ll integrate AI-driven insights with existing security tooling and document methodologies for peer review. This position sits at the intersection of advanced AI and high-assurance security in a global financial context, offering a chance to shape proactive protection at scale.
Pay / Benefits
diverse and inclusive environment
accessible recruitment process with accommodations
flexible, supportive work culture
Responsibilities
Run frontier AI models against SWIFT codebases to identify vulnerabilities conventional tools miss
Develop experimental methodology for this work
Create scalable AI-assisted detection pipelines including deduping and routing issues to remediation
Conduct head-to-head technical evaluations of frontier models on real detection tasks
Integrate AI-assisted detection into SWIFT software development processes with current security tooling
Identify vulnerability classes not visible to current tooling and develop detection approaches
Operate within SWIFT governance and tooling controls
Defend technical decisions and document methodologies for peer scrutiny
Key requirements
Hands-on experience applying AI/LLM models to real security testing or vulnerability research
Strong software engineering ability to read and reason about large codebases across multiple languages
Deep knowledge of application security fundamentals including vulnerability classes and analysis tools
Proven ability to build tools and pipelines from scratch (scripting, automation, integration)
Experience designing and running structured technical evaluations or experiments and drawing defensible conclusions
Comfort with ambiguity and ability to originate technical approaches without a playbook
Clear technical communication to peer security engineers under scrutiny
Clear technical communication
Comfort with ambiguity
Ability to originate a technical approach
AI/LLM integration for security testing
Software engineering across multiple languages
Static, dynamic, and dependency analysis principles
We use essential cookies to make this site work. With your permission we would also like to use the optional cookies below. Nothing optional is set until you choose, and you can change your mind at any time from "Cookie settings" at the bottom of every page. Cookie policy.
Essential — keep the site working and secure, and remember the choice you make here. Always on.