Sr Principal Software Engineer, AI Security Platform
Posted Sep 21, 2026 · We last checked this listing on Oct 6, 2026
Likely interview questions for this role
Written from this job description, not a generic list. Each one notes what the interviewer is really checking.
About your past
Tell me about a user-facing application you built for developers. How did you make it something they wanted to use?
What they are checking: Whether they can build good front-end experiences, which the posting says the role must cover.
What would you do
A new, better AI model comes out every few months. How would you design the platform so switching models is safe?
What they are checking: Whether they build abstraction and regression testing to swap models without breaking results.
As the platform owner, how do you decide what to build next when security teams and developers want different things?
What they are checking: Whether they can take ownership of priorities and balance needs of different users.
About the work
How would you design an AI-powered code security scanner that finds real vulnerabilities without drowning developers in false positives?
What they are checking: Whether they understand that precision and validation decide whether developers trust a security tool.
How would you validate a vulnerability an AI model reports before showing it to a developer?
What they are checking: Whether they think about confirming findings, which the posting describes as identify, validate and report.
How do you handle the risk that source code sent to a frontier AI model could leak sensitive information?
What they are checking: Whether they consider data protection and vendor controls when integrating outside AI services at a bank.
Walk me through how you would evolve the architecture of a platform like this as the codebase it scans grows to thousands of repositories.
What they are checking: Whether they can plan for scale in cost, throughput and model limits like context size.
How would you measure whether the scanner is actually getting better over time?
What they are checking: Whether they would build evaluation sets and track precision and recall instead of trusting anecdotes.
How do you defend an AI-powered tool against prompt injection hidden in the code it is scanning?
What they are checking: Whether they understand new attack paths that come with putting untrusted input into AI models.
How would you secure the cloud-native infrastructure that runs this platform?
What they are checking: Whether they can protect their own security tool, which would be a high-value target.
Practice this interview out loud.
Offer builds a real interview for this exact role at Northern Trust from your resume and this job description, asks the questions one at a time, and tells you what landed. The first one is free.
Practice this out loudThe full job description
As published by Northern Trust.