Ramp AI Coding Round, Experienced SWE Onsite: 3 Experiences

Shared by janebeingjane ·
Company
Ramp
Reports
3 interview reports
Level
Full-time
Stages
Onsite

Ramp's 2026 AI coding round for experienced engineers meant building inside a codebase Ramp provided; all three candidates were rejected.

At a glance

  • Process: recruiter call and a tech screen (03), then an onsite of coding on CoderPad, system design, the AI coding round and behavioral (03).
  • Asked recently: a matching system in a provided repo (01), receipt upload matched to transactions with an OCR service (02), and a finance feature in a larger downloaded repo (03). The tech screen in 03 was a link-following maze.
  • Difficulty: 02 called it average and 03 hard; 03's feedback was that Ramp wanted more understanding of the AI's output. The repo in 03 logged every prompt for the interviewer to read.
  • Practise first: Retryable URL Maze and Ramp's project coding bank.

Coverage: Experienced full-time software engineers: two changing jobs and one recently laid off · The AI coding round at the onsite, plus the tech screen and the other onsite rounds where one candidate described them · Interviews in April–June 2026 (2) and July–September 2026 (1), reported July 9–21, 2026 · No locations given

What came up

In all three reports, Ramp's AI coding round meant building on an existing repo or codebase rather than solving a puzzle from scratch. Two of the three tasks were about matching, and the one candidate who got feedback was told they failed the AI round for not showing enough understanding of what the AI wrote.

Topic Reports Last seen
AI round inside a repo or codebase Ramp provided 3 of 3 Jul 2026
A matching task 2 of 3 Jul 2026
AI tools set up by the candidate on their own machine 2 of 3 Jul 2026
Optional bonus items once the main task is done 1 of 3 Jul 2026
Frontend work on an upload flow backed by an OCR service 1 of 3 Jul 2026
A finance feature in a larger codebase, short on time 1 of 3 Jul 2026
Interviewer reviewing the candidate's prompts afterward 1 of 3 Jul 2026

A report can count toward more than one row. Report 01 didn't say what its matching system matched.

Questions we found

AI Coding

Question Reports Last seen
Build a matching system in a provided repo, any language, then pick bonus items if time is left 1: 01 Jul–Sep 2026
Redesign receipt upload so a new OCR service extracts the details and suggests the matching transaction, with the user confirming or changing the match 1: 02 Apr–Jun 2026
Build a finance feature in a larger downloaded repo with local AI, with every prompt logged to history.txt 1: 03 Apr–Jun 2026

Algorithms / Data Structures

Question Reports Last seen
Retryable URL Maze: explore a maze of linked URLs, with follow-ups on 4xx and then 5xx responses 1: 03 Apr–Jun 2026

System Design

Question Reports Last seen
Present a system you designed before, with slides and diagrams 1: 03 Apr–Jun 2026

3 detailed candidate timelines, loops, and screens

01: A matching system, paid for with a $50 tools stipend

Report date: Jul 21, 2026 · Interview period: Jul–Sep 2026 · Role: Software engineer · Experience: changing jobs, came through a headhunter · Result: Rejected

Onsite: AI live coding

  1. Ahead of the round, Ramp gave a $50 stipend to set up whichever AI tools the candidate wanted.
  2. Ramp supplied a repo. The job was to build a matching system in it, in any language.
  3. If the main part got done with time to spare, the candidate could choose a few bonus items to take on.

That's all the author shared about the task. They didn't say what the system matched, what the bonus items were, or how the other onsite rounds went. Their own read afterward: a round like this probably looks past whether you can build the thing, at how you break down the requirements and how you check what the AI generates. They rated the difficulty average.


02: Receipt upload and auto-matching, on a codebase Ramp shared

Report date: Jul 18, 2026 · Interview period: Apr–Jun 2026 · Role: Software engineer · Experience: changing jobs · Result: Rejected

Onsite: AI-enabled interview

  1. Ramp shared an existing codebase and asked the candidate to improve the UI and UX of one flow.
  2. The problem with the current flow: attaching receipts is tedious. A user has to find the transaction, open it, and upload receipts one at a time.
  3. The backend team had already shipped an OCR service. You give it a receipt image, it pulls out the amount, merchant and date, and it suggests which transaction the receipt belongs to. Each call takes a few seconds.
  4. The task was a better upload-and-match experience: let users upload receipts, show processing status while the OCR runs, display what it extracted, and let the user confirm the suggested transaction or pick a different one.

The candidate called the difficulty average and the overall experience negative.


03: A finance feature against the clock, with every prompt on record

Report date: Jul 9, 2026 · Interview period: Apr–Jun 2026 · Role: Software engineer · Experience: laid off about two months before posting · Result: Rejected

Recruiter call

  1. About 20 minutes.

Tech screen

  1. A maze you explore by following links, which the author described as a known question. Practice version: Retryable URL Maze.
  2. The follow-ups were about failed requests: first handling 4xx responses, then 5xx. The practice version covers retrying 503s and malformed responses, but not the 4xx follow-up.
  3. After the screen, the process moved over to a different team.

Onsite

Four rounds, which could be done in person or remotely. The author was under an NDA, so they shared impressions rather than exact prompts.

Round 1: Coding on CoderPad

  1. A practical problem about financial transactions, not an algorithm puzzle.
  2. The interviewer cared about object-oriented design, clean code and corner cases. The concrete task wasn't described.

Round 2: System design

  1. The candidate presented a system they had designed in the past, with slides and diagrams.
  2. It was judged against the level they were interviewing for.

Round 3: AI coding

  1. The interviewer gave them a repo to download, and they used AI running on their own machine to build a feature in it. The feature was finance-related, much like the CoderPad round, but the codebase was a lot bigger.
  2. Time was very tight. Waiting for the AI to answer, reading what came back and iterating all ate into it, and there was no time to read every function. The candidate had to keep doing other work while the AI ran.
  3. The repo's Claude.md told the AI to record every prompt from the session in a file called history.txt. Afterward, the interviewer went through that file to judge how the candidate had worked with the AI.
  4. The candidate used five prompts in total.
  5. This was the round they failed. The feedback said Ramp wanted to see more understanding of the AI's output, rather than taking it as it came.

Round 4: Behavioral

  1. Routine, by the author's account. No questions were named.

They rated the loop hard overall.


Patterns across the reports

  1. The work starts from Ramp's code. All three candidates (01, 02 and 03) built inside a repo or codebase Ramp handed them. Two of them brought their own AI setup: 01 got a stipend to pick tools, and 03 ran AI locally on a downloaded repo. Report 02 doesn't say which AI tools were available.

  2. Matching and money. Reports 01 and 02 both centered on matching: a matching system in 01, and receipts matched to transactions in 02. Since 01 never said what was being matched, there's no way to tell whether it was the same exercise. Reports 02 and 03 both had finance tasks, receipts in one and an unnamed finance feature in the other.

  3. Understanding the AI's code came up twice, in different ways. In 03 it was the stated reason for failing the AI round, and the interviewer had a full log of the candidate's prompts to look at. In 01 it's the candidate's own guess about what the round measures, with no feedback behind it.

Common questions

What is the Ramp AI coding interview?

A build task inside a repo or codebase Ramp provides, using AI tools: a matching system (01), a receipt upload flow (02) or a finance feature (03).

Does Ramp check how you use AI in the interview?

In 03, the repo's Claude.md logged every prompt to history.txt and the interviewer reviewed it afterward; the feedback asked for more understanding of the AI's output.

Keep practicing

AI coding rounds at other companies

More companies with AI rounds on FastPrep:

Across companies: 2026 AI Coding OAs at 15 Companies: 32 Reported Problems and 2025–2026 AI Coding Phone Screens and Onsites at 43 Companies: 76 Reported Problems.

Sources: Anywhere useful interview info can be found.

0 total reactions. Your reactions: none.

Comments

0

No comments yet — be the first to share what you know.