Cresta Interview Experiences

5 results

• 

  Five Timed OA Parts for the FDE RoleCresta · Software Engineer · Online Assessment · Oct 2026

  I applied for the Cresta Forward Deployed Engineer (FDE) role, on the AI Agent side. I just finished the OA, and it is very different from the usual pure-algorithm OA. Overall it leans toward practical coding, understanding requirements, and real engineering ability. Sharing the question types for reference. The OA has 5 parts in total, each one timed separately, with these limits: 10 / 30 / 20 /…

• 

  AI-Assisted Coding Round: Build a Flight-Booking Chat Agent in PythonCresta · Software Engineer · Onsite · Sep 2026

  You get an api.md doc plus an agent_starter.py file, and you have to use AI assistance to implement an AI Agent that searches for and books flights. The format is a chat dialog. Note: the language has to be Python, and you need to set up the whole project in your own IDE, so make sure you can actually run Python locally first. They'll also give you OPENAI_API_KEY, OPENAI_BASE_URL, and FLIGHT_API_…

• 

  Phone Screen Building a Least-Load Job DispatcherCresta · Software Engineer · Technical Screen · Sep 2026

  Write a Job Dispatcher-Executor system. You are tasked with implementing a simple job dispatcher that distributes incoming jobs to a pool of executors (i.e., workers). Each job is represented as an integer (its ID), and executors are dynamically added and removed during runtime. You must define two classes: Executor – Represents a worker that can accept jobs. LoadBalancer – Maintains a list of ex…

• 

  System Design Round: Build an Eval Platform for AI AgentsCresta · Software Engineer · Onsite · Sep 2026

  System design round They have you design an eval system to evaluate the results of an Agent using different models, e.g. tool usage, response speed, plus testing different system prompts, that kind of thing. The original question is below: > Design a system for evaluating AI agents. Users of the system are going to be teams developing AI agents, e.g. agents which automatically analyze contact cen…

• 

  A Feature-Flag Evaluation Engine, Then Rejected After a ‘Great Chat’Cresta · Software Engineer · Onsite · Jul 2026

  Rejected

  I used Claude to help organize this write-up. The interviewer kept saying he really enjoyed our conversation, and then rejected me anyway. Problem background: you're given three JSON files and asked to implement a feature-flag evaluation engine that maps every user to a final boolean value (on/off) for every flag. Input files: flags.json — definitions for 7 flags user.json — 10,000 users expected…