Luma AI interview questions

Showing 1–7 of 7 results

• Build Collaborative Document Editing Shared by People and AI AgentsMedium

  A take-home asks you to build collaborative document editing in which people and AI agents edit the same document, then defend its scaling limits and add approval, audit history and selective revert for agent edits. Tests concurrency control, real-time sync, anchoring slow agent edits, attribution, and prototype scoping.

  Luma AISoftware EngineerSystem DesignOnsite
• Build a Scalable Text-to-Speech Service Prototype, Then Defend and Extend ItMedium

  An 8 to 12 hour take-home asks you to build a scalable text-to-speech service with AI coding agents, then defend its trade-offs and scaling limits in a product review and plan a new customer requirement. Tests 0-to-1 scoping, streaming and batch synthesis design, capacity reasoning, and estimation and roadmap skills.

  Luma AISoftware EngineerSystem DesignOnsite
• Explain Your Motivation and How You Use AI Development Tools in Your WorkflowMedium

  A recruiter screen for an AI product engineering role asks about your motivation for moving, why this company, your hands-on experience with AI development tools and workflows, and which areas of development interest you. Tests concrete, verifiable examples of agent-assisted work and a coherent career story.

  Luma AISoftware EngineerBehavioral & LeadershipOnsite
• Implement Refactoring Assessment FeaturesHard

  This problem tests your ability to manage stateful data with temporal versioning and reconstruct valid paths in a graph while ensuring data integrity under constraints.

  Luma AISoftware EngineerCoding & AlgorithmsTechnical Screen
• Manage Prompt and Model Behavior in ProductionHard

  This question tests the ability to design an end-to-end configuration management and observability system for LLM applications that ensures reproducibility, safety, and rapid recovery from performance drift.

  Luma AISoftware EngineerML System DesignTechnical Screen
• Reverse-Engineer an App's Undocumented API and Rebuild It With Better UXMedium

  A take-home asks you to reverse-engineer the undocumented API behind an existing app and rebuild the app with a better user experience, then review its fragility and extend it with safe write support. Tests API discovery, schema inference, resilient client design, credential and legal judgment, and UX scoping.

  Luma AISoftware EngineerSoftware Engineering FundamentalsOnsite
• Solve Seven Python Image and Data TasksMedium

  This problem tests foundational proficiency in NumPy array manipulation, mathematical function implementation, and geometric logic, which are essential for low-level image processing tasks.

  Luma AIMachine Learning EngineerCoding & AlgorithmsTechnical Screen