Jobs › Chicago Trading Company
AI Engineer
Posted Sep 11, 2026 · We last checked this listing on Oct 6, 2026
Apply at Chicago Trading Company
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 project where you went from a vague idea to something running in production. What did the ambiguous part look like, and how did you resolve it?
What they are checking: ability to self-direct through undefined problems without needing a spec handed to them
What have you built with this technology on your own time, outside of work?
What they are checking: genuine personal engagement with the field versus resume-driven interest
Tell me about a time a tool or workflow you built for other engineers got pushback, or wasn't adopted the way you expected. What did you do?
What they are checking: how they handle building for internal users and whether they iterate based on feedback
Describe a case where you had to choose between a quick fix and building the underlying infrastructure properly. How did you decide?
What they are checking: judgment about when to invest in common infrastructure versus ship fast, relevant to their stated dual focus
What would you do
Say you're bringing a new coding agent or harness into the firm. How would you evaluate whether it's actually better than what engineers already use?
What they are checking: judgment on model/harness tradeoffs and whether they'd rely on hype versus real benchmarking
You're building a tool for traders, not engineers. How does your approach to the interface or the workflow change compared to building something for other developers?
What they are checking: whether they can adapt technical work to different user sophistication and actually talk to non-engineers
Suppose a quant asks you to prototype an agent for backtesting or simulation work. What questions would you ask before writing any code?
What they are checking: whether they'd dig into the actual workflow and constraints before building, given no finance background is assumed
About the work
Walk me through an agent or LLM-based tool you built end to end. What did the system look like, and what was the hardest part to get right?
What they are checking: whether they've actually shipped agent tooling versus just called an API once
Tell me about a time you had to design context or tool access for an agent so it didn't do something it shouldn't. How did you think about access controls or guardrails?
What they are checking: awareness of security and access control concerns in agent infrastructure, not just capability
How would you approach tracing and debugging an agent pipeline when something goes wrong three steps into a multi-step task?
What they are checking: depth of hands-on experience with observability in agentic systems versus theoretical familiarity
If inference latency became a bottleneck for a shared internal service, what levers would you look at first?
What they are checking: real understanding of inference infrastructure and performance tradeoffs, not just model-layer knowledge
How comfortable are you moving between Python, C++, and Java on the same project, and can you give an example where that mix actually mattered?
What they are checking: verifying claimed language breadth is real rather than a checkbox
How do you think about evaluating whether a model or agent is actually good at a task, especially before it has a track record in production?
What they are checking: depth on evaluation and benchmarking methodology, called out as a nice-to-have but core to reliability
Practice this interview out loud.
Offer builds a real interview for this exact role at Chicago Trading Company 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 Chicago Trading Company.
Apply at Chicago Trading Company