Cohere
Mid
Build the workflow/agent execution engine inside Cohere's North enterprise AI platform
This interview probes full-stack product engineering (Python/React) on Cohere's Agents & Automations team, building the workflow builder, execution engine, integrations, and observability tooling behind North. Expect deep dives on shipping RAG/agentic systems at scale, working under security/privacy constraints that block using popular libraries, and comfort operating across the stack in a fast-moving, ambiguous environment.
Step into this interview
Free · a live voice mock calibrated to this exact role
What this interview tests
- Full-stack shipping in Python and React in production
- Building/deploying RAG or agentic applications at meaningful scale
- Engineering under strict security/privacy constraints (no popular libraries, low-resource environments)
- Workflow/execution-engine design: builder, integrations, observability, evaluation loops
- Debugging and fixing issues outside your own codebase
Common question themes
Describe a RAG or agentic system you built and deployed to real users — what broke at scale and how did you fix it?
Tell me about a time you couldn't use a popular library/tool due to security or deployment constraints — what did you build instead?
How would you design observability and evaluation for an agent workflow so customers can trust what it does?
Walk through debugging an issue that lived outside your own part of the codebase
How do you operate when priorities and objectives shift mid-project?
Related interviews
Cohere
Mid
Forward Deployed Engineer, Agentic Platform
Cohere
Mid
Member of Technical Staff, Applied ML
Cohere
Senior
Data Engineer, Data Foundations
Affirm
Mid
Software Engineer II, Full-Stack (Marketplace Performance)
Netflix
Senior
Senior Full Stack Software Engineer 4/5 - Client and Partner Technologies
Replit
Mid