Bank of America·AI Engineer·Onsite - Coding / Algorithms
Sep 2026
Ran a newly designed AI Engineer interview this week and came away genuinely shaken by how far ahead the candidates were operating. Built a PR-review exercise around catching bugs in agent-generated code, and two of the three candidates basically told me the whole premise was outdated.
- How would you approach quality assurance in a safety-critical system where serious bugs are completely unacceptable, if you're not reading the code you generate?
- Walk us through how you'd review a high-risk, agent-generated pull request that touches critical business logic, and how you'd drive any fixes you find.
- What does your current workflow look like for managing code quality when you're generating most or all of the code with AI tools?
“I asked this expecting to catch someone out, and the answer I got was something like 'if I were doing healthcare or aerospace work I'd probably look closely at code review, maybe even write the checks myself.' My first reaction was that this was a non-answer from someone used to shipping PoCs.”