Applied AI Security Engineer

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.

• diverse and inclusive environment
• accessible recruitment process with accommodations
• flexible, supportive work culture

• 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

• 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